dataset
stringclasses 4
values | id
stringlengths 5
13
| messages
listlengths 2
6
|
|---|---|---|
flan_v2
|
flan_v2_88160
|
[
{
"content": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given an article, a question which often contains a blank and four options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer (from the given options) for the question from the given article and return one of the options from \"A\", \"B\", \"C\", and \"D\". Do not generate anything else apart from one of the following characters: \"A\", \"B\", \"C\", \"D\". There is only one correct answer for each question.\nExample: Article: Homework can put you in a bad mood , and that might actually be a good thing. Researchers from the University of Plymouth in England doubted whether mood might affect the way kids learn. To find out the answer, they did two experiments with children. The first experiment tested 30 kids. Someshapes were hidden inside a different, larger picture. The kids had to find the small shapes while sitting in a room with either cheerful or sad music playing in the background. To test their mood, the scientists asked the kids to point to one of five faces, from happy to sad. Children who listened to cheerful music tended to point to the smiley faces while the others pointed to the unhappy ones. The researchers found that sad kids took at least a second less to find the small shapes. They also found an average of three or four more shapes. In the second experiment, 61 children watched one of two scenes from a film. One scene was happy, and the other was sad. Just like in the first experiment, kids who saw the sad scene acted better compared to the others. The researchers guessed that feeling down makes people more likely to focus on a problem or difficult situation. Not all scientists agree with them, however. Other studies argued that maybe, that cheerful music in the first experiment distracted kids from finding shapes. While scientists work on finding out the answers, it still might be wise to choose when to do your tasks according to your mood. After eating a delicious ice cream, for example, write an essay. \n Question: Researchers did experiments on kids in order to find out _ . \n Options: (A) how they really feel when they are learning (B) whether mood affects their learning ability (C) what methods are easy for kids to learn (D) the relationship between sadness and happiness\nOutput: B\nIt is clearly mentioned in the article that to the check effect of mood on children is the main purpose of the experiment. So, B is the correct answer.\n\nNew input case for you: Article: A whale that became stranded in the River Thames in Central London has died after attempts to save its life failed. The whole nation had been hoping for a more successful outcome to the attempted rescue, updates of which were shown on TV news programmes throughout the day and night. The five- meter long bottle-nosed whale, which probably weighted about four tones, was first spotted in the river on Friday. There had been reports that a pod of whales had swum into the Thames Estuary earlier in the week, which caused terror among naturalists, as this kind of whale only thrives in much deeper water. It was the first sighting of the endangered species in the Thames since records began nearly a century ago. There was no more news of the pod, which suggests that most of them turned back and swam out to sea. However, one whale clearly became separated from this group. Incredibly, the first person to raise the alarm was a man who saw the giant mammal from the train he was on when it crossed the river. Almost immediately, a rescue attempt was mounted and further attempts to move the whale began on Saturday morning. After unsuccessfully attempting to gently encourage it to swim downstream of its own accord towards the Thames Estuary and eventually the sea, rescuers decided to move it onto the barge . The rescue operation involved winching the whale onto an inflatable raft which had been placed on the barge. 3,000 onlookers watched as the whale was treated with extreme care by the rescuers and applauded when the transfer operation was complete. The barge then set off with the intention of freeing the whale in deeper water. Sadly, it began to convulse during the journey and died. Earlier in the day, naturalist and TV presenter Terry Nuktins had warned that attempts to move the large mammal were misguided and that the proximity of the rescuers to the whale was potentially disastrous. He said that the whale would have been terrified by the people around it and it wouldn't have been used to the sight of boats and the noise of the engines and propellers. \n Question: People throughout the country learned about the attempted rescues by_. \n Options: (A) listening to the radio (B) reading newspapers (C) watching TV news (D) asking some rescuers\nOutput:",
"role": "user"
},
{
"content": "C",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_79491
|
[
{
"content": "You will be given a definition of a task first, then some input of the task.\nThis task is about translating a given Yoruba language sentence to English.\n\nArákùnrin Gamaliel Camarillo, tó jẹ́ agbẹnusọ fún àwa Ẹlẹ́rìí Jèhófà ní Mexico sọ pé: “Ó dùn wá gan-an pé wọ́n ń gbéjà ko àwọn ará wa tó jẹ ẹni àlàáfíà tó sì ń bọ̀wọ̀ fún àṣà àwọn míì, torí pé wọn ò bá wọn lọ́wọ́ nínú àwọn àṣà ẹ̀sìn tí kò bá ẹ̀rí ọkàn wọn mu.\nOutput:",
"role": "user"
},
{
"content": "Brother Gamaliel Camarillo, a spokesman for Jehovah’s Witnesses in Mexico, explains: “We are truly appalled that our fellow worshippers, who live peacefully in their community and respect local customs, have been attacked simply because they will not participate in religious rites that offend their conscience.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86216
|
[
{
"content": "In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.\n\n[EX Q]: Statement: These claims can't, after all, all be right. Choices: 1. These claims are right. 2. These claims made by the girls can't be correct. 3. These claims can not be right.\n[EX A]: 1\n\n[EX Q]: Statement: and then i listen to it when i'm in the car driving to work because again there's you know there's nothing else going on i might as well listen to the radio while i'm driving to work but other than that i've i really don't Choices: 1. I never listen to anything in the car. 2. When I'm in the car, I listen to NPR. 3. WHen I'm in the car, I listen to that.\n[EX A]: 1\n\n[EX Q]: Statement: they will already have in fact i have one myself i'm reluctant to admit Choices: 1. I'm not ashamed to admit that I do not have one myself. 2. They already have an introductory novel on physics. 3. It's not easy for me to admit that I have one myself.\n[EX A]:",
"role": "user"
},
{
"content": "1\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_85066
|
[
{
"content": "Part 1. Definition\nIn this task, you will be shown an extract from a movie plot and a question. You need to provide the correct answer for it. Short answers containing words that are present in the passage are preferred.\nPart 2. Example\nTwenty-year-old Will Hunting of South Boston is a self-taught, genius-level intellect, though he works as a janitor at the Massachusetts Institute of Technology and spends his free time drinking with his friends, Chuckie (Ben Affleck), Billy (Cole Hauser) and Morgan (Casey Affleck). When Professor Gerald Lambeau (Stellan Skarsgård) posts a difficult mathematics problem as a challenge for his graduate students, Will solves the problem anonymously, stunning both the graduate students and Lambeau himself. As a challenge to the unknown genius, Lambeau posts an even more difficult problem. Lambeau chances upon Will solving the problem but Will flees the scene. That night at a bar, Will meets Skylar (Minnie Driver), a British student about to graduate from Harvard, who plans on attending medical school at Stanford and gives Will her phone number before leaving., Question: How old is Will Hunting in the movie ?\nAnswer: Answer: Twenty years\nExplanation: This is a good example which results in a factoid answer.\nPart 3. Exercise\nIn 1860s post-U.S. Civil War Texas, Jim Coates (Fess Parker) leaves home to work on a cattle drive, leaving behind his wife Katie (Dorothy McGuire), older son Travis (Tommy Kirk) and younger son Arliss (Kevin Corcoran).While Jim is away, Travis sets off to work in the cornfield, where he encounters \"Old Yeller\" (Spike), a Labrador Retriever/Mastiff mix. He was called that because \"yeller\" is an eye dialect pronunciation of yellow and the fact that his bark sounds more like a human yell. Travis unsuccessfully tries to drive the dog away, but Arliss likes him and defends him to Travis. However, the dog's habit of stealing meat from smokehouses and robbing hens' nests does not endear him to Travis.Later, Arliss tries to capture a black bear cub by feeding it cornbread and grabbing it. Its angry mother hears her cub wailing and attacks, but Old Yeller appears and drives her off, earning the affection of the family. Travis grows to love and respect Old Yeller, who comes to have a profound effect on the boy's life.Old Yeller's owner, Burn Sanderson (Chuck Connors), shows up looking for his dog, but comes to realize that they need him more than he does, and agrees to trade him to Arliss in exchange for a horny toad and a home-cooked meal. Sanderson takes Travis aside and warns him of the growing plague, hydrophobia (rabies).One day, Travis sets out to trap feral hogs. On the advice of Bud Searcy (Jeff York), he sits in a tree, trying to rope them from above as Old Yeller keeps them from escaping. Travis falls into the group of hogs, one of which injures him. Old Yeller attacks it and rescues Travis, who escapes with a badly hurt leg. Old Yeller is seriously wounded as well. Searcy warns them of hydrophobia in the area and is chastised by Katie for trying to scare Travis. Fortunately, the boars did not have hydrophobia, and both Travis and Old Yeller fully recover.However, the family soon realize that their cow, Rose, has not been allowing her calf to feed and may have rabies. Watching her stumble about, Travis confirms it and shoots her. While Katie and Lisbeth Searcy (Beverly Washburn) burn the body that night, a rabid wolf attacks. Old Yeller defends the family but is bitten in the struggle before Travis can shoot and kill the wolf. They pen Old Yeller in the corn crib for several weeks to watch him. Soon when Travis goes to feed him, he growls and snarls at him. After he nearly attacks Arliss, who, not understanding the danger, had attempted to open the corn crib, a grieving Travis is forced to shoot him. In doing so, he takes his first step toward adulthood.Heartbroken from the death of his beloved dog, Travis refuses the offer of a new puppy fathered by Old Yeller. Jim comes home with a bagful of money and presents for his family. Having learned about Old Yeller's fate from Katie, he explains the facts about life and death to Travis. When they get back to the farm, the young puppy steals a piece of meat, a trick he learned from his father. Travis adopts him, naming him \"Young Yeller\" in honor of his father., Question: Who drives the cub's mother off?\nAnswer:",
"role": "user"
},
{
"content": "Answer: Old Yeller",
"role": "assistant"
}
] |
cot
|
cot_82241
|
[
{
"content": "Yes / no, is the following a verifiable fact?\n\"The Hagia Sophia happens to be one of the most popular tourist attractions in Turkey.\"\nyes\nThe Hagia Sophia is a historical landmark in Istanbul, Turkey.\n**Q**\nIs the following statement true?\n\"The Compact disc remains popular even after the advent of mp3 players and smartphones.\"\n**A**\nno\nSmartphones have replaced the compact disc as the music storage device of choice.\nDoes the following sentence make sense?\n\"The novel Pride and Prejudice was inspired by Dante's Inferno.\"\nOptions:\n- yes\n- no\nno\nThe two novels are nothing alike and from different time periods.\n**Q**\nIs the following sentence factually correct?\n\"Formula One contestants solve math formulas in less than one second.\"\nOptions:\n- yes\n- no\n**A**\nno\nFormula One is a type of car racing, not a type of math contest.\nDoes the following sentence make sense?\n\"Fax begins with the recipient name and ends with the signature of the sender.\"\nOptions:\n- yes\n- no\nno\nFax is actually an office equipment and not a message document.\nClaim: \"One can find that QR code is an automatic identification and data capture that can link you to a site.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\n",
"role": "user"
},
{
"content": "yes\nRestaurants use them, websites use them for promotional reasonings.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_88137
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nContext word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.\nSolution: The trophy doesn't fit into the brown suitcase because _ is too small.\nWhy? Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question.\n\nNew input: Context Word: towel. \nQuestion: James spread a towel over the water on the table and he got the _ dry. \nAnswer: table.\nSolution:",
"role": "user"
},
{
"content": "James spread a towel over the water on the table and he got the _ wet.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_83626
|
[
{
"content": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\nExample Input: 5, 10, ['D', 'G', '187', '1977', 't', '4397', '1091', '9253', '3527', 'j', 'X', 'e', '8527', 'm', '7621', '7853', '8331', '8193', '3031', 'O']\nExample Output: j, 3527, 9253, 1091, 4397, t\n\nExample Input: 6, 7, ['S', '4201', 'H', 'K', 'L', '8827', 'o', '9979', 'r', '9743', 'T']\nExample Output: o, 8827\n\nExample Input: 6, 18, ['f', '3355', '5337', '5601', '9107', 'i', '8323', '2211', 'S', 'm', '6647', 'S', 'r', 'i', '425', '8851', '9875', '3827', '2477', '4051']\nExample Output:",
"role": "user"
},
{
"content": "3827, 9875, 8851, 425, i, r, S, 6647, m, S, 2211, 8323, i\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_78259
|
[
{
"content": "Definition: The input is a conversation between an automated system and a user, followed by a question. The user is looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Similarly, the user may ask details of the place suggested by the system such as phone number, address, etc. The answer of the question has to be a Yes or a No. Given such a dialogue, answer the given question based on the information present in the dialogue.\nInput: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'id like to find an expensive restaurant'\nSystem: 'Are you looking for somewhere near a particular venue? For example, Cherry Hinton Water Play, Downing College, or King's College.'\nUser: 'and it should be in the castle hill area'\nSystem: 'What type of food would you like? For example, Chinese take away, American, or Vegetarian.'\nUser: 'an expensive restaurant'\nSystem: 'Are you looking for somewhere near a particular venue? For example, Cambridge Contemporary Art, or Kettle's Yard.'\nUser: 'french would be fine'\nSystem: 'What part of town do you have in mind? For example, something in the Addenbrooke's, Arbury, or Fen Ditton area.'\nUser: 'castle hill'\nSystem: 'Are you looking for somewhere near a particular venue? For example, Magdalene College, Saint Catharine's College, or Wandlebury Country Park.'\nUser: 'castle hill area'\nSystem: 'What part of town do you have in mind? For example, something in the Cherry Hinton, Chesterton, or central area.'\nUser: 'castle hill area'\nSystem: 'What part of town do you have in mind? For example, something in the Arbury, Girton, or New Chesterton area.'\nUser: 'castle hill'\nSystem: 'What part of town do you have in mind? For example, central, or King's Hedges.'\nUser: 'castle hill'\nSystem: 'Are you looking for somewhere near a particular venue? For example, the Broughton House, or the Museum of Archaelogy and Anthropology.'\nUser: 'i would like to find an expensive restaurant'\nSystem: 'Are you looking for somewhere near a particular venue? For example, All Saints Church, the Museum Of Technology, or the Scott Polar Museum.'\nUser: 'do you have any french restaurants'\nSystem: 'Are you looking for somewhere near a particular venue? For example, All Saints Church, the Museum Of Technology, or Pembroke College.'\nUser: 'technology'\nSystem: 'The Hotel du Vin is a great restaurant, it serves french food and it's in the expensive price range.'\nUser: 'all saints church'\nSystem: 'The Hotel du Vin is an outstanding restaurant, it serves french food and it's in the expensive price range.'\nUser: 'can i have the phone number and'\nSystem: 'The phone number of the Hotel du Vin is 01223227330.'\nUser: 'postcode'\nSystem: 'The Hotel du Vin is in the area with the postcode CB2 1QA.'\nUser: 'for the du vin could i have the unintelligible'\nSystem: 'The Hotel du Vin is an outstanding restaurant.'\nUser: 'postcode'\nSystem: 'The Hotel du Vin is in the area with the postcode CB2 1QA.'\nUser: 'could i have the post code please'\nSystem: 'The Hotel du Vin is in the area with the postcode CB2 1QA.'\nUser: 'i'\nSystem: 'The Hotel du Vin is an outstanding restaurant.'\nUser: 'and the hotel du vins phone number'\nSystem: 'Would you like a french food, or you don't care?'\nUser: 'could i have the phone number please'\nSystem: 'Would you like a french food, or you don't care?'\nUser: 'french food'\nSystem: 'The phone number of the Hotel du Vin is 01223227330. It's in the area with the postcode CB2 1QA.'\nUser: 'french food'\nSystem: 'The Hotel du Vin, which serves french food, is an outstanding restaurant. It's in the expensive price range.'\nUser: 'thank you and good bye'\nQuestion: 'Did the user mention any cuisine preferences?'\n\nOutput:",
"role": "user"
},
{
"content": "No",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_90518
|
[
{
"content": "In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.\n\nExample input: [5797, 8817, '8297', 'b', 'U', 'b'], [5843, 8809, '8297', 'b', 'W', 'C']\nExample output: 8297, b\nExample explanation: Here, '8297, b' is the longest common subsequence in both the input lists [5797, 8817, '8297', 'b', 'U', 'b'] and [5843, 8809, '8297', 'b', 'W', 'C'].\nQ: [8293, 2523, 6671, 'j', 'G', 'e', 'O', 'C', 9751, 8541, 'j', '3289', '2933', 'd', '10017', '1727', '9971', '5501', 'k', '4915', '2235', '2675', '5361', '9713', '4179', '3523', '8429', '4441', 'V', '9213', 'Y', 'O', 'z', 5401, 5745, 'v', 8545], ['N', 'N', 1881, 'j', '3289', '2933', 'd', '10017', '1727', '9971', '5501', 'k', '4915', '2235', '2675', '5361', '9713', '4179', '3523', '8429', '4441', 'V', '9213', 'Y', 'Q', 'l', 'S', 6023, 'F', 5215, 4435]\nA:",
"role": "user"
},
{
"content": "j, 3289, 2933, d, 10017, 1727, 9971, 5501, k, 4915, 2235, 2675, 5361, 9713, 4179, 3523, 8429, 4441, V, 9213, Y",
"role": "assistant"
}
] |
cot
|
cot_54702
|
[
{
"content": "[QUESTION] Premise: \"A woman is working with some kind of messy machinery at a party.\"\nHypothesis: \"A woman at a party is using a machine.\"\nDo we know that the hypothesis entailed by the premise?\nOne would have to be working with machinery in order to be using a machine.\nThe answer is yes.\nQ: Given the sentence \"A cute little kid with a little green price sticker on his nose.\" is it true that \"A kid has a sticker on his nose.\"?\nA: A cute little kid is a way of describing a kid.\nThe answer is yes.\nQUESTION: Given the sentence \"A big bald man with checkered button up shirt and brown knee high shorts taking a picture of something on the ground.\" can we conclude that \"The man is naked and alone in the bathroom.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: If you're naked then you are not wearing a shirt and shorts.\nThe answer is no.\n[QUESTION] Given the sentence \"A tennis player with green a green headband on is ready to hit the ball.\" is it true that \"The football player removes his helmet.\"?\nThe tennis player and football player are two completely different people.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A man is working under a white vehicle while a child watches him.\"\nHypothesis: \"A younger man is working on a car.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A man is not necessarily a younger man and a vehicle is not necessarily a car.\nThe answer is it is not possible to tell.\n[QUESTION] Test for natural language inference.\nPremise: \"A man is wearing a hat and a white shirt.\"\nHypothesis: \"The man is wearing a hat.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n",
"role": "user"
},
{
"content": "You cannot be wearing a shirt and a hat at the same time.\nThe answer is yes.",
"role": "assistant"
}
] |
cot
|
cot_52848
|
[
{
"content": "Q: Test for natural language inference.\nPremise: \"Man putting a key into a lock.\"\nHypothesis: \"A man is picking a lock.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: You don't put a key into a lock if you are trying to pick the lock.\nThe answer is no.\nQUESTION: If \"A group of young people gathered around a woman in a gallery of artistic vases.\" does that mean that \"The young people are at the gallery for a school trip.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The fact that a there is a a group of young people at a gallery doesn't imply that they are there for a school trip.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"Kids at the soccer field are getting ready for the game.\" is it true that \"Kids are preparing for a game.\"?\nGetting ready for something is the same as preparing for it.\nThe answer is yes.\nQ: Can we conclude from \"Asian little kids in a school waiting for a teacher.\" that \"The teacher is late for school.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The kids waiting for teacher does not imply the teacher is late.\nThe answer is it is not possible to tell.\nQUESTION: Test for natural language inference.\nPremise: \"A man sits on the steps in a street as his child plays happily on the stairs.\"\nHypothesis: \"A man watches from afar since he cannot interact with his child.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: A man sits on the steps as his child plays on the stairs does not imply the man watches from afar since he cannot interact with his child.\nThe answer is it is not possible to tell.\nQUESTION: Premise: \"A young boy wearing a clever black and white shirt with his head bowed down.\"\nHypothesis: \"A boy is weaing a plad white and brown shirt.\"\nDo we know that the hypothesis entailed by the premise?\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "The boy is not wearing a plaid white and brown shirt. He is wearing a black and white shirt.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
cot
|
cot_51074
|
[
{
"content": "[QUESTION] Test for natural language inference.\nPremise: \"A woman with a box of candy standing with a man who is holding some of the candy.\"\nHypothesis: \"A bald man is holding some candy.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nSentence one about a woman with a box of candy with a man doesn't describe the man being bald.\nThe answer is it is not possible to tell.\nQ: Can we conclude from \"A small child is digging in the dirt while another small child watches in a garden.\" that \"Two small children outside.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Two small children can be a better way of avoiding redundancies in referring to both a small and another small child.\nThe answer is yes.\nQUESTION: Given the sentence \"A dog jumping through the air getting hit by water.\" is it true that \"A dog sleeping in its bed.\"?\n\nLet's solve it slowly: A dog that is jumping through the air is not sleeping.\nThe answer is no.\n[QUESTION] Given the sentence \"Two mothers stroll their children in the park.\" is it true that \"During the beginning of autumn.\"?\nThe mothers and children in their strollers are outside in the park.\nThe answer is yes.\nQ: If \"A girls volleyball team in a huddle.\" does that mean that \"A volleyball team huddles.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The team huddles and team in a huddle are two different construals of the same event.\nThe answer is yes.\n[QUESTION] Can we conclude from \"A naked little girl being thrown into the air.\" that \"A girl is in the air.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n",
"role": "user"
},
{
"content": "Being thrown into the air implies that the girl is in the air at the time the statement is made.\nThe answer is yes.",
"role": "assistant"
}
] |
cot
|
cot_55579
|
[
{
"content": "Q: Can we conclude from \"Two small children happily playing on a tire swing.\" that \"The kids are sliding on the jungle gym.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Two small children is a very specific statement compared to The kids which is very vague.\nThe answer is no.\nQUESTION: Given the sentence \"Man on the beach is throwing a red ball.\" can we conclude that \"A man is on his porch drinking beer.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The man ca not be throwing a ball on the beach if hes on his porch drinking beer.\nThe answer is no.\n[QUESTION] Test for natural language inference.\nPremise: \"Several people gather in the street in front of owen's.\"\nHypothesis: \"Several people are watching street performers outside of owen's.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nSeveral people gather in the street in front of Owen's does not necessary that they are watching street performers outside of Owen's.\nThe answer is it is not possible to tell.\nQ: Premise: \"Several people are milling about outside a large off-white colored house with a terra cotta roof while someone in the distance takes their picture.\"\nHypothesis: \"Family walking in on party.\"\nDo we know that the hypothesis entailed by the premise?\nA: People walking in somewhere in a group is different than a group milling around.\nThe answer is no.\nQUESTION: Can we conclude from \"People taking pictures while the sun is setting.\" that \"Tourists take pictures during sunset.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: The people taking pictures of the sunset are not necessarily tourists.\nThe answer is it is not possible to tell.\nQUESTION: Premise: \"Three women talking outside.\"\nHypothesis: \"Three women are outside talking and looking over at another woman on a bench.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Three women talking outside are not necessarily looking over at another woman and not necessarily on a bench.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
cot
|
cot_54816
|
[
{
"content": "Q: Given the sentence \"A man with his young children.\" can we conclude that \"The man doesn't know the kids.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A man who is with his young children will definitely know the kids.\nThe answer is no.\nQUESTION: Given the sentence \"A curly-haired little girl watering plants with a hose.\" can we conclude that \"A straight-haired little girl is picking flowers.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: You cannot be curly-hair ed and straight-haired at the same time.\nThe answer is no.\n[QUESTION] Given the sentence \"Two asian ladies in pink dresses with white hats on laughing at something in the distance.\" can we conclude that \"Two ladies are in pink.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nThe two Asian ladies wearing pink dresses are in pink clothing.\nThe answer is yes.\nQ: Test for natural language inference.\nPremise: \"A man on a cellphone standing with a woman.\"\nHypothesis: \"A man on a cellphone is talking to his mistress while standing with his wife.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The man with cell phone does not imply he is talking with his mistress.the woman standing beside him need not be his wife.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A boy wearing his school band uniform is standing holding his trumpet.\" can we conclude that \"A boy holds a trumpet.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A boy must be holding his trumpet in order to hold it.\nThe answer is yes.\nQUESTION: Premise: \"A group of adults are standing under a tree in front of a red brick house.\"\nBased on this premise, can we conclude that the hypothesis \"A class reunion.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "The group of adults doesn't mean they are a class reunion.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91354
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\n\nJacob entered the dining_room. William entered the dining_room. The tomato is in the green_drawer. William exited the dining_room. Jacob moved the tomato to the blue_cupboard. Jacob is in the dining_room. Olivia entered the dining_room. The cucumber is in the blue_cupboard. Olivia exited the dining_room. Jacob moved the cucumber to the green_drawer. William entered the pantry. Jacob entered the pantry. The asparagus is in the red_cupboard. Jacob exited the pantry. William moved the asparagus to the green_pantry. Abigail entered the hall. William entered the hall. The persimmon is in the blue_pantry. William exited the hall. Abigail moved the persimmon to the blue_envelope. Where does Abigail think that William searches for the persimmon?\nSolution: blue_pantry\nWhy? The persimmon was last in the blue_pantry before William exited the hall. After William exited the hall, Abigail moved the persimmon to the blue_envelope, so she knows where William will look for it.\n\nNew input: Alexander entered the living_room. William entered the living_room. The banana is in the blue_container. Alexander moved the banana to the blue_box. Oliver entered the porch. William entered the porch. The pear is in the blue_suitcase. Oliver moved the pear to the green_suitcase. Alexander entered the back_yard. Ethan entered the back_yard. The cucumber is in the red_crate. Alexander moved the cucumber to the blue_envelope. Alexander entered the porch. Oliver is in the porch. The pear is in the green_suitcase. Alexander moved the pear to the blue_suitcase. Where does Alexander think that Oliver searches for the pear?\nSolution:",
"role": "user"
},
{
"content": "blue_suitcase",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82614
|
[
{
"content": "Part 1. Definition\nYou are given a statement written in Oriya. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .\nPart 2. Example\nStatement: 'ରକନୁଦ୍ଦୀନ'ଙ୍କ ଶାସନ ବହୁତ କମ ସମୟ ପାଇଁ ଥିଲା । ଇଲତୁତମିଶଙ୍କ ବିଧବା , ଶାହା ତୁର୍କାନଙ୍କ ଶାସନ ଉପରେ ନିୟନ୍ତ୍ରଣ ରହି ପାରିନଥିଲା । ଭୋଗ ବିଳାସୀ ଏବଂ ଦାଇତ୍ୱହୀନ ରକନୁଦ୍ଦୀନଙ୍କ ବିପକ୍ଷରେ ଜନତା ମାନଙ୍କ ମଧ୍ୟରେ ଏହି ସୀମା ପର୍ଯ୍ୟନ୍ତ ଆକ୍ରୋଶ ଭାବ ଜାଗ୍ରତ ହୋଇଥିଲା କି , ୧ ନଭେମ୍ବର ୧୨୩୬ ମସିହାରେ ରକନୁଦ୍ଦୀନ ତଥା ତାଙ୍କ ମାତା , ଶାହା ତୁର୍କାନଙ୍କ ହତ୍ୟା କରିଦିଆଗଲା । ତାଙ୍କ ଶାସନ ମାତ୍ର ୬ ମାସର ଥିଲା । ଏହା ପରେ ସୁଲତାନଙ୍କ ପାଇଁ ଅନ୍ୟ କୌଣସି ବିକାଶର ଅଭାବରେ ମୁସଲମାନଙ୍କୁ ଏକ ମହିଳାଙ୍କୁ ଶାସନର ବାଗଡୋର ଦେବାକୁ ପଡ଼ିଥିଲା , ଏବଂ ପରେ ରଜିୟା ସୁଲତାନ <MASK>ର ଶାସିକା ରୂପେ ନିୟୋଜିତ ହୋଇଥିଲେ ।ଶାସନ କ୍ଷେତ୍ରରେ ରଜିୟଙ୍କ ରୁଚି ନିଜ ପିତାଙ୍କ ଶାସନ ସମୟରୁ ହିଁ ରହିଥିଲା ।\n\n Option A: ଭାରତ\n\n Option B: ଭଟିଣ୍ଡା\n\n Option C: ଦିଲ୍ଲୀ\n\n Option D: ରାଜସ୍ଥାନ\nAnswer: ଦିଲ୍ଲୀ\nExplanation: The most suitable word from the given options to replace the <MASK> token is ଦିଲ୍ଲୀ, as Azi Sultan was the ruler of Delhi and at those times the remaining places aren't related .\nPart 3. Exercise\nStatement: |<MASK>, locally Known as \"Nandikeshwari\" temple. Only 1.5 km from the railway station under a banyan tree within a boundary wall, Birbhum district, West Bengal, India\n\n Option A: Gujarat\n\n Option B: Meghalaya\n\n Option C: Rajasthan\n\n Option D: Sainthia\nAnswer:",
"role": "user"
},
{
"content": "Sainthia",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_90430
|
[
{
"content": "In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\nOne example is below.\nQ: Title: Marcus Buys Khakis. Marcus needed clothing for a business casual event. He decided to buy a pair of khakis. The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked. c. All of his clothes were either too formal or too casual.\nA: ac\nRationale: Marcus is buying clothes for a business event and not presenting an idea.\nQ: Title: John was riding his motorcycle. The bike flipped. John broke his arm and had to get a cast. Choices: a. All of a sudden he swerved to avoid a pothole. b. He was going fast down the road. c. The trip was fun and allowed Ryan to rest before returning to work.\nA:",
"role": "user"
},
{
"content": "ab",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87555
|
[
{
"content": "Given a passage in simplified Chinese, generate a reading comprehension question. The question should be unambiguous and the answer to this question should be in the passage.\n\nLet me give you an example: Passage: 《战国无双3》（）是由光荣和ω-force开发的战国无双系列的正统第三续作。本作以三大故事为主轴，分别是以武田信玄等人为主的《关东三国志》，织田信长等人为主的《战国三杰》，石田三成等人为主的《关原的年轻武者》，丰富游戏内的剧情。此部份专门介绍角色，欲知武器情报、奥义字或擅长攻击类型等，请至战国无双系列1.由于乡里大辅先生因故去世，不得不寻找其他声优接手。从猛将传 and Z开始。2.战国无双 编年史的原创男女主角亦有专属声优。此模式是任天堂游戏谜之村雨城改编的新增模式。本作中共有20张战场地图（不含村雨城），后来发行的猛将传再新增3张战场地图。但游戏内战役数量繁多，部分地图会有兼用的状况，战役虚实则是以光荣发行的2本「战国无双3 人物真书」内容为主，以下是相关介绍。（注：前方加☆者为猛将传新增关卡及地图。）合并本篇和猛将传的内容，村雨城模式剔除，战国史模式可直接游玩。主打两大模式「战史演武」&「争霸演武」。系列作品外传作品\nThe answer to this example can be: 《战国无双3》是由哪两个公司合作开发的？\nHere is why: The output is a question related to the passage. It is asking for the companies who created the game mentioned in the passage. This is a good question.\n\nOK. solve this:\nPassage: 上地雄辅，日本的男演员、艺人，同时是组合「羞耻心」的成员（「心」担当）。出生于神奈川县横须贺市，身高178cm，体重67kg，血型O型。所属经纪人公司为日本音乐娱乐。小学及初中时代曾代表日本出战世界赛。初中时代为软式棒球队横须贺Stars的队长。其后受到38间高球的升读邀请，入读棒球名校私立横滨高等学校，并加入该校的硬式棒球部，担任捕手。为松坂大辅（现属波士顿红袜）的前辈。高中二年级时，在甲子园预选比赛中，右肘神经断裂，将正选位置让给后辈小山良男（现属中日龙）。高中毕业前在里原宿被星探发掘，自此以演员为目标。1999年在TBS电视剧《L×I×V×E》中正式出道。2007年6月27日起，参演富士电视台问答游戏节目《Quiz! Hexagon II》，并以「蠢材」著名，与里田舞、鹤野刚士、木下优树菜、スザンヌ及野久保直树并称为「Hexagon笨蛋六人组」。在预选笔试中，共21次成为最低分的参加者，为该节目的最多纪录。2007年8月1日，在《Quiz! Hexagon II》中，把「羞耻心」（しゅうちしん）念成さじしん，自此与鹤野刚士和野久保直树组成的组合，被岛田绅助命名为「羞耻心」。2008年3月5日，在《Quiz! Hexagon II》中首次演出单曲《羞耻心》。4月9日正式发售，即登上Oricon单曲榜第2位。\nAnswer:",
"role": "user"
},
{
"content": "上地雄辅是哪个国家的男演员？",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87684
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the numerical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no numerical element is in the list.\n\n['r', '1647', 'K', 'b', '3151', 'I']\n2, 5\n\n['3691', '999', 'N', 'G', '7019', '1519', '3297', 'L', 'f', '85', 'l', '193', '8093', '5763', 'C', 'k', '5017', '7951', 'a', 'm', 'a', 'T', 'O', 'q', '5099', '7841', 'X', '1741', '6899', '609', 'y', '6019', 'h', 'A', '9823', '8247', '7615', 'w', '9067']\n1, 2, 5, 6, 7, 10, 12, 13, 14, 17, 18, 25, 26, 28, 29, 30, 32, 35, 36, 37, 39\n\n['4883', '8265', '4665', '7345', '4075', '2473', 'Z', '783', '2641', 't', 'f', 't', '511', '287']\n",
"role": "user"
},
{
"content": "1, 2, 3, 4, 5, 6, 8, 9, 13, 14\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84522
|
[
{
"content": "Your task is to generate the next utterance in a given dialogue. You will be given a few sentences describing the personality of the person who is making the dialogue, and a history of the dialogue after that. Each line in the history is said by one of the two participants in the conversation.\n\nEx Input:\nPersonality: I enjoy swimming.\nI am a secretary.\nI've 3 cats.\nMy favorite color is orange.\nI like tacos.\nChat history: -Hey there, cannot wait till taco tuesday.\n -I would eat a taco while listening to linking park.\n -I wouldn't care lol I just want to swim before summer over.\n -I could watch someone swimming but they wouldn't hear me.\n\nEx Output:\nLl that is cool I love the fall since I love orange.\n\n\nEx Input:\nPersonality: My favorite meal is steak.\nI only sleep 3 hours a day.\nI always travel alone.\nI have no parents or siblings.\nI'm incredibly smart.\nChat history: -Hi, I am very smart. Are you?\n -That all depends on what you mean by smart, yet I can be quite confident.\n\nEx Output:\nI need only sleep for 3 hours a day and have no siblings or parents.\n\n\nEx Input:\nPersonality: I am an artist.\nI recently got a cat.\nI love watching game of thrones.\nI enjoy walking for exercise.\nChat history: -Hello how are you? Just finished some painting.\n -Very good, you? I just hiked in my pink boots.\n -Cool I get my exercise from walking.\n -Great. You might enjoy hiking then. Its my favorite thing, especially the appalachian trail.\n -If only I could take my nee cat!\n -You could bring the cat to my marketing firm.\n -Lets chat after game of thrones!\n -Sounds great and we can listen to some folk music!\n -I need to finish this painting today.\n -What is the painting of?\n -My new kitten watching game of thrones!\n -Excellent! Maybe could you paint the appalachian trail for me?\n -Yes! I could walk it for inspiration.\n -Absolutely! I could let you borrow my pink hiking boots if you like.\n\nEx Output:\n",
"role": "user"
},
{
"content": "Perfect! Would make walking easier! Thanks.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_14410
|
[
{
"content": "Question: Sentence A: The elegant Renaissance style lends an unaccustomed sophistication to the nightmarish superstitions of medieval Brittany incorporated in the sculpture.\n\nSentence B: The opposing styles really work well together. \n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: it is not possible to tell\n\n\nQuestion: Sentence A: because um oh about the time i got out of working that long hours was when the uh when the twins were about three years old and uh they never you know i don't think they noticed i wasn't around that much you know with all the children around the house it's kind of hard to notice that dad isn't around very much um\n\nSentence B: I was always around.\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: no\n\n\nQuestion: Sentence A: As you reach the Atlantic coast, you'll become almost engulfed in vast groves of banana trees, with bunches hanging temptingly close to the road.\n\nSentence B: As you reach the Atlantic coast, you will find some of the best tasting bananas.\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: it is not possible to tell\n\n\nQuestion: Sentence A: Research and development is composed of basic research, applied research, and development.\n\nSentence B: Applied research is not a part of research and development.\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer:",
"role": "user"
},
{
"content": "no",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_88373
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\n[EX Q]: Context Word: read. \nQuestion: Jenny decided to read her book in the garden instead of in the house, because it was too dark in the _ . \nAnswer: house.\n[EX A]: Jenny decided to read her book in the garden instead of in the house, because it was brighter in the _ .\n\n[EX Q]: Context Word: hormone. \nQuestion: The doctor injected the hormone through the neck rather than the arm, as the _ was receptive to circulate it. \nAnswer: neck.\n[EX A]: The doctor injected the hormone through the neck rather than the arm, as the _ was hesitant to circulate it.\n\n[EX Q]: Context Word: connection. \nQuestion: She had to fix the connection between the modem and the router, but the _ was giving her more problems. \nAnswer: modem.\n[EX A]:",
"role": "user"
},
{
"content": "She had to fix the connection between the modem and the router, but the _ was giving her less problems.\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_79687
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nContext Word: motor. \nQuestion: The motor that we got online was not able to be put in the vehicle because the _ was too huge. \nAnswer: motor.\n",
"role": "user"
},
{
"content": "The motor that we got online was not able to be put in the vehicle because the _ was too tiny.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_90221
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\nOne example: Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.\nSolution is here: The trophy doesn't fit into the brown suitcase because _ is too small.\nExplanation: Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question.\n\nNow, solve this: Context Word: wash. \nQuestion: She had to wash the shirt several times to clean it, but the dress required only a rinse, as the _ was so grimy. \nAnswer: shirt.\nSolution:",
"role": "user"
},
{
"content": "She had to wash the shirt several times to clean it, but the dress required only a rinse, as the _ was so clean.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_88529
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nExample Input: Context Word: cafeteria. \nQuestion: The teacher removed students from the cafeteria and took them to the classroom until the _ was empty. \nAnswer: cafeteria.\nExample Output: The teacher removed students from the cafeteria and took them to the classroom until the _ was full.\n\nExample Input: Context Word: fabric. \nQuestion: The choice of fabric for the clothes instead of using a composite was made because the _ was pliable. \nAnswer: fabric.\nExample Output: The choice of fabric for the clothes instead of using a composite was made because the _ was stiff.\n\nExample Input: Context Word: culture. \nQuestion: Their culture was a lot harder to adapt to than my atmosphere because the _ was very strict. \nAnswer: culture.\nExample Output:",
"role": "user"
},
{
"content": "Their culture was a lot harder to adapt to than my atmosphere because the _ was very lenient.\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82939
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nLet me give you an example: Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.\nThe answer to this example can be: The trophy doesn't fit into the brown suitcase because _ is too small.\nHere is why: Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question.\n\nOK. solve this:\nContext Word: marriage. \nQuestion: we had a great marriage ceremony, a beautiful dress and ring. The _ was shiny. \nAnswer: ring.\nAnswer:",
"role": "user"
},
{
"content": "we had a great marriage ceremony, a beautiful dress and ring. The _ was clear.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82766
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nEx Input:\nContext Word: gym. \nQuestion: Winston went to the gym to get in shape, and decided to run on the treadmill and lift weights. The _ helped him lose weight. \nAnswer: treadmill.\n\nEx Output:\nWinston went to the gym to get in shape, and decided to run on the treadmill and lift weights. The _ helped him increase muscle mass.\n\n\nEx Input:\nContext Word: quiet. \nQuestion: She left the library to go study at home, since the _ was insufficiently quiet for concentrating. \nAnswer: library.\n\nEx Output:\nShe left the library to go study at home, since the _ was adequately quiet for concentrating.\n\n\nEx Input:\nContext Word: pattern. \nQuestion: The pattern was replaced with a new design for the marketing campaign because the _ was uninspiring. \nAnswer: pattern.\n\nEx Output:\n",
"role": "user"
},
{
"content": "The pattern was replaced with a new design for the marketing campaign because the _ was inspiring.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89903
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nLet me give you an example: Context word: fit. \nQuestion: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer: trophy.\nThe answer to this example can be: The trophy doesn't fit into the brown suitcase because _ is too small.\nHere is why: Here, replacing the trigger word \"large\" by its antonym \"small\" flips answer to the second object (\"suitcase\") in the question. So, this is a valid question.\n\nOK. solve this:\nContext Word: belt. \nQuestion: The woman wore the belt around her waist instead of her hips because the _ were wider. \nAnswer: hips.\nAnswer:",
"role": "user"
},
{
"content": "The woman wore the belt around her waist instead of her hips because the _ was narrower.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_73972
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nContext Word: hospital. \nQuestion: Arthur went to the neighborhood clinic instead of the hospital because the _ was expensive. \nAnswer: hospital.\n",
"role": "user"
},
{
"content": "Arthur went to the neighborhood clinic instead of the hospital because the _ was affordable.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_83641
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\n[Q]: Context Word: quiet. \nQuestion: She left the library to go study at home, since the _ was insufficiently quiet for concentrating. \nAnswer: library.\n[A]: She left the library to go study at home, since the _ was adequately quiet for concentrating.\n\n\n[Q]: Context Word: boss. \nQuestion: Kyle's boss gave him the pen to use instead of the pencil because the _ was easier to read. \nAnswer: pen.\n[A]: Kyle's boss gave him the pen to use instead of the pencil because the _ was harder to read.\n\n\n[Q]: Context Word: paternity. \nQuestion: Declaring paternity is important for official records like medical records but not credit records because the _ are restricted. \nAnswer: medical records.\n[A]:",
"role": "user"
},
{
"content": "Declaring paternity is important for official records like medical records but not credit records because the _ are open.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82172
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nEx Input:\nContext Word: phone records. \nQuestion: The subpoenas issued by the judge included the client's personal phone records, because the the _ were incriminating. \nAnswer: phone records.\n\nEx Output:\nThe subpoenas issued by the judge included the client's personal phone records, because the the _ was exhaustive.\n\n\nEx Input:\nContext Word: middle. \nQuestion: The statue fit in the middle of the shelf, but the bookend did not, because the _ was thin. \nAnswer: statue.\n\nEx Output:\nThe statue fit in the middle of the shelf, but the bookend did not, because the _ was thick.\n\n\nEx Input:\nContext Word: hands. \nQuestion: She wanted to put her child's cold hands in the gloves but the _ were too large. \nAnswer: gloves.\n\nEx Output:\n",
"role": "user"
},
{
"content": "She wanted to put her child's cold hands in the gloves but the _ were too small.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87991
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\n[Q]: Context Word: Concierge. \nQuestion: The concierge recommended taking the subway instead of a taxi to the play, because the _ would be faster. \nAnswer: Subway.\n[A]: The concierge recommended taking the subway instead of a taxi to the play, because the _ would be slower.\n\n\n[Q]: Context Word: claim. \nQuestion: Jenna filled out the paperwork to file a claim against the construction company, even though the _ was very long. \nAnswer: paperwork.\n[A]: Jenna filled out the paperwork to file a claim against the construction company, even though the _ was very risky.\n\n\n[Q]: Context Word: risky. \nQuestion: The man took a walk in the park instead of in the woods because it was less risky in the _ . \nAnswer: park.\n[A]:",
"role": "user"
},
{
"content": "The man took a walk in the park instead of in the woods because it was more risky in the _ .\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91374
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\n[Q]: Context Word: survived. \nQuestion: More of the roses survived than the carnations because the _ had been planted in worse soil. \nAnswer: carnations.\n[A]: More of the roses survived than the carnations because the _ had been planted in rich soil.\n\n\n[Q]: Context Word: bed. \nQuestion: His bed had bed bugs which he hoped were only in the bedding so he bought a new set but not a new mattress since the _ was dirty. \nAnswer: bedding.\n[A]: His bed had bed bugs which he hoped were only in the bedding so he bought a new set but not a new mattress since the _ was clean.\n\n\n[Q]: Context Word: hair. \nQuestion: Sheila didn’t check the temperature of her flat iron before straightening hair. The _ was hot. \nAnswer: iron.\n[A]:",
"role": "user"
},
{
"content": "Sheila didn’t check the temperature of her flat iron before straightening her hair. The _ was fried.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_72936
|
[
{
"content": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nContext Word: butt. \nQuestion: The man thought that the girls butt would be important instead of her heart, but the _ is vital. \nAnswer: heart.\n",
"role": "user"
},
{
"content": "The man thought that the girls butt would be important instead of her heart, but the _ is lifeless.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_85601
|
[
{
"content": "TASK DEFINITION: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\nPROBLEM: Title: Secret Note. Sentence 1: It said I know what you've did. Sentence 2: The rock had a note on it. Sentence 3: Gill got hit behind her by a rock. Sentence 4: Gill panicked and went to the police. Sentence 5: Her report was rejected by the police team.\n\nSOLUTION: 13\n\nPROBLEM: Title: Falling down. Sentence 1: Fortunately, after a few minutes it stopped hurting so bad. Sentence 2: It really hurt when I fell. Sentence 3: I fell down playing basketball the other day. Sentence 4: I was able to get up and play again. Sentence 5: That was a really lucky turn of events.\n\nSOLUTION: 13\n\nPROBLEM: Title: The Shy Actress. Sentence 1: He practiced with her on how to overcome her shyness. Sentence 2: She was rather shy about being on stage. Sentence 3: The drama teacher had to build up Helen courage. Sentence 4: Helen was invited to join the school play by her drama teacher. Sentence 5: Helen was eventually able to speak her lines in the play out aloud.\n\nSOLUTION:",
"role": "user"
},
{
"content": "41\n\n",
"role": "assistant"
}
] |
cot
|
cot_97338
|
[
{
"content": "Teacher: One of the following sentences is nonsensical. Which one is it?\nOptions:\n- Sentence A: \"He wrote those code on a Macintosh\"\n- Sentence B: \"He wrote those code on a calculator\"\n\nStudent: We cant wrote calculator because it is a device used for arithmetic operation.\nThe answer is Sentence B.\nquestion in book:\nWhich of these sentences doesn't make sense?\nOptions:\n- Sentence A: \"Cows chew water\"\n- Sentence B: \"Cows chew cud\"\n\nstandard solution:\nWater is not a solid and can not be chewed on.\nThe answer is Sentence A.\n[TEACHER] Pick which sentence is not logical.\nOptions:\n- Sentence A: \"bridges are built to attract tourists\"\n- Sentence B: \"bridges are built to cross rivers\"\n\n[Student] Bridges are a form of necessary transport, not attractions to tourists.\nThe answer is Sentence A.\nTeacher: Pick which sentence is not logical.\nOptions:\n- Sentence A: \"He took a bath to get clean.\"\n- Sentence B: \"He took a car ride to get clean.\"\n\nStudent: A car ride does not make you clean.\nThe answer is Sentence B.\nquestion in book:\nPick which sentence is not logical.\nOptions:\n- Sentence A: \"You put on sun screen before going out into the sun.\"\n- Sentence B: \"You put on cooking oil before going out into the sun.\"\n\nstandard solution:\nCooking oil cannot protect your skin from the sun.\nThe answer is Sentence B.\nTeacher: One of the following sentences is nonsensical. Which one is it?\nOptions:\n- Sentence A: \"janice felt ashamed of the scar on her face\"\n- Sentence B: \"janice felt ashamed of the smile on her face\"\n\nStudent:",
"role": "user"
},
{
"content": "A smile would not cause someone to feel shame.\nThe answer is Sentence B.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_65996
|
[
{
"content": "Based on this review, would the user recommend this product? === Review: Found this tape very useful for the intermediate player. Has some intermediate to advanced chops on finger style flat top that are the roots of a lot of electric blues. I've been picking songs off by ear for years but Keb Mo has some exotic sounding but simple chords- if you see where they are played. Beats the hell out of $30.00 worth of private lessons! Answer:\n\nAnswer: Yes\n\n\nBased on this review, would the user recommend this product? === Review: The book seems geared for children, maybe teenagers. The message is simple, the world doesn't owe you anything, well duh! I would be mad if a supervisor gave me this book, and any company that has handed it out, needs to make some changes of their own. A much better book is Leap by Rick Smith, check it out. Answer:\n\nAnswer: No\n\n\nBased on this review, would the user recommend this product? === Review: A comic masterpiece? Hardly. Didn'tlaugh once. Might have been funny in 1886, but it sure isn't now. Anyway, the book is not what I was looking for, which was serious historical fiction--an imaginative re-telling of this intriguing, long-lost story. I found it afterwards in the novel by Donna Woolfolk Cross, which is very well-researched, beautifully written, and deeply moving. That's the one to get, not this boring and unfunny \"comic masterpiece\". Answer:\n\nAnswer:",
"role": "user"
},
{
"content": "No",
"role": "assistant"
}
] |
cot
|
cot_87669
|
[
{
"content": "QUESTION: If \"A brown and black dog playing in the snow.\" does that mean that \"There are dogs playing outdoors.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: There are two colored dogs which are generally dogs and snow is outdoors.\nThe answer is yes.\n[QUESTION] Given the sentence \"A person in an apron is selling many different sized fish on a stand.\" is it true that \"A person is selling fish.\"?\nSelling many different sized fish is a sufficient condition for selling fish.\nThe answer is yes.\nQ: Premise: \"A man handing a baby off to a woman.\"\nHypothesis: \"A man shows the baby to a woman.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Handing a baby off to someone is different from shows the baby to someone.\nThe answer is it is not possible to tell.\nQUESTION: If \"A man is sitting on a bed with four guitars.\" does that mean that \"A person is on a bed with guitars.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A man sitting on a bed with four guitars must be a person who is on a bed with guitars.\nThe answer is yes.\n[QUESTION] Premise: \"Five children dressed in black cloaks and hats.\"\nBased on this premise, can we conclude that the hypothesis \"The children are wearing cloaks and hats on their way to school.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nThe children's clothes do not imply that they are on their way to school.\nThe answer is it is not possible to tell.\nQ: If \"A young girl wearing a red dress is holding up a toy doll.\" does that mean that \"A girl has a doll.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "A girl holding a toy doll implies that she has a doll.\nThe answer is yes.",
"role": "assistant"
}
] |
cot
|
cot_88766
|
[
{
"content": "QUESTION: Can we conclude from \"A boy jumps off of an open air staircase.\" that \"A boy commits suicide.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: Not all jumping off staircases involves an attempt to commit suicide.\nThe answer is it is not possible to tell.\n[QUESTION] If \"An older woman walks down a frescoed sidewalk outside of a gun store called \"\"dave's\"\".\" does that mean that \"A woman is about to go buy a gun from the gun store.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nWalking by a store does not imply she'll buy from the store.\nThe answer is it is not possible to tell.\nQ: Test for natural language inference.\nPremise: \"A very colorful bus is pulled off to the side of the road as its passengers load.\"\nHypothesis: \"A stopped bus is picking people up.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The bus could be just dropping people off and not necessarily be picking people up.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A team of rowers rowing in a green and red boat.\" can we conclude that \"The men are playing tennis.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The team cannot be playing tennis while they are rowing a boat.\nThe answer is no.\n[QUESTION] Premise: \"Two women are sitting in rose-colored wing back chairs as one points over her shoulder at a colorful human figure.\"\nBased on this premise, can we conclude that the hypothesis \"The women are at the beach.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nWing back chairs are intended to be placed inside not on a beach.\nThe answer is no.\nQ: Can we conclude from \"A woman in high heels and a man in jeans walk past a black and white wall mural.\" that \"A woman and man are playing a game of tennis.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA:",
"role": "user"
},
{
"content": "People don't wear high heels or jeans when playing a game of tennis.\nThe answer is no.",
"role": "assistant"
}
] |
cot
|
cot_52211
|
[
{
"content": "Q: Given the sentence \"A little girl asleep on the street next to a change bowl.\" can we conclude that \"A little girl sleeping next to a change bowl.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: yes\nChain-of-thought: The little girl on the street was sleeping next to a change bowl.\n\nQ: Given the sentence \"A man in a cap instructs a bald man with a pool cue how to strike the ball.\" is it true that \"Two men playing pool.\"?\nA: yes\nChain-of-thought: A man with a pool cue to strike the ball must be playing pool.\n\nQ: Given the sentence \"A guy in a black shirt coming through the door with two bags of ice.\" can we conclude that \"A guy drives his car to the stadium.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: no\nChain-of-thought: A guy drives his car to the stadium can not also be coming through the door.\n\nQ: If \"A woman lays on a floating platform in the middle of a body of water.\" does that mean that \"The woman is running on water.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: no\nChain-of-thought:",
"role": "user"
},
{
"content": "The woman is floating in the middle of a body of water.",
"role": "assistant"
}
] |
cot
|
cot_74128
|
[
{
"content": "Q: If \"The boy in blue runs with the ball whilst being chased by two boys in red.\" does that mean that \"The boy in blue is running with a cube.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: no\nChain-of-thought: The boy either has a ball or he has a cube.\n\nQ: Given the sentence \"A small car drives on two wheels on a village street.\" can we conclude that \"A large truck is on the highway.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: no\nChain-of-thought: A vehicle can not be both a car and a truck. One can be driving on a street or a highway but not both simultaneously.\n\nQ: Test for natural language inference.\nPremise: \"An acrobat doing a handstand on top of a pole with legs spread in a v.\"\nHypothesis: \"The acrobat was performing at the circus.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: it is not possible to tell\nChain-of-thought: The acrobat could perform many places other than at the circus.\n\nQ: Given the sentence \"A person in red rock climbing.\" is it true that \"A mountain in the background.\"?\nA: it is not possible to tell\nChain-of-thought:",
"role": "user"
},
{
"content": "A person is practicing climbing on the rock wall beneath a real mountain.",
"role": "assistant"
}
] |
cot
|
cot_91203
|
[
{
"content": "[QUESTION] Given the sentence \"Three gentlemen playing a board game.\" is it true that \"Some people are fighting over cards.\"?\nThe three gentlemen do not fight over cards as they play a board game.\nThe answer is no.\nQ: Premise: \"A blond child with blue eyes and an elmo shirt sitting in a car.\"\nBased on this premise, can we conclude that the hypothesis \"A child is watching a movie on the dvd player.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A child in a car is not implied to be watching a movie on the DVD player.\nThe answer is it is not possible to tell.\nQUESTION: If \"A tattooed.\" does that mean that \"Shirtless young man in a cap and blue jeans carries a skateboard.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A young man with tatoos is heading to meet friends and skateboard.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"Old asian white hair man getting an outdoor haircut from a man using a black comb and portable electric shaver while being protected form falling hair by a red and white cloth patterned with red scissors and women portraits squares.\" can we conclude that \"This is a paid transaction.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nNot all haircut are paid for. Some haircuts can be given for free.\nThe answer is it is not possible to tell.\nQ: Test for natural language inference.\nPremise: \"A woman in an orange athletic outfit playing tennis.\"\nHypothesis: \"There is no match today.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A woman is either playing tennis or there is no match today.\nThe answer is no.\n[QUESTION] Can we conclude from \"A man in a green shirt positions a sheep for clipping with electric sheers.\" that \"Man under water.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n",
"role": "user"
},
{
"content": "A man positioning a sheep for clipping with electric sheers cannot be under water at the same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_88366
|
[
{
"content": "You are given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the 5 given options and report that option.\n\n[EX Q]: Question: What does the hexa number E78 in radix 7.\n\n Option A: 12455\n\n Option B: 14153\n\n Option C: 14256\n\n Option D: 13541\n\n Option E: 14541\n[EX A]: Option D\n\n[EX Q]: Question: A candidate scoring 25% in an examination fails by 30 marks , while another candidate scores 50 % mark, gets 20 marks more than the minimum pass marks . Find the minimum pass marks. Find the minimum pass percentage.\n\n Option A: 26\n\n Option B: 40\n\n Option C: 88\n\n Option D: 27\n\n Option E: 26\n[EX A]: Option B\n\n[EX Q]: Question: Can you replace the question mark with the correct number, given the pair of numbers exhibits similar relationship?\n? : 3839 :: 11 : 1209\n\n Option A: 6\n\n Option B: 16\n\n Option C: 26\n\n Option D: 36\n\n Option E: 46\n[EX A]:",
"role": "user"
},
{
"content": "Option B\n\n",
"role": "assistant"
}
] |
cot
|
cot_80298
|
[
{
"content": "Q: If \"Five people are on their yard with two of them climbing a ladder to a tree in the background.\" does that mean that \"Five people are climbing a ladder to a tree.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Five people are watching the two climbing while the other Five are all climbing.\nThe answer is no.\nQUESTION: Can we conclude from \"A man sits on a pile of rugs by a building while three more men and a woman stand nearby.\" that \"A man sits on rugs that he is selling.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: Sentence 1: A man sits on a pile of rugs by a building while three more men and a woman stand nearby. Sentence 2: A man sits on rugs that he is selling.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"Blacksmith at working outdoors.\" can we conclude that \"Irons smith are taking a lunch break.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nOne cannot be working outdoors and taking a lunch break at the same time.\nThe answer is no.\nQ: Given the sentence \"A male street performer walking a tightrope.\" can we conclude that \"An elephant is juggling at the circus.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A male street performer will be a human being not an elephant.\nThe answer is no.\nQUESTION: Premise: \"A surfer dressed in black catches a huge wave and starts riding on the descent.\"\nHypothesis: \"A man is waiting to get on the bus.\"\nDo we know that the hypothesis entailed by the premise?\n\nLet's solve it slowly: Catching a huge wave requires a surfboard and the person needs to be in the water which cannot happen when you are waiting for the bus.\nThe answer is no.\nQUESTION: Premise: \"Young east asian children in sports jerseys in a track and field activity.\"\nBased on this premise, can we conclude that the hypothesis \"Young east asian children from the track and field team.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Just because young East Asian children from the track and field team doesn't mean they are in sports jersey.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84854
|
[
{
"content": "TASK DEFINITION: You are given a statement written in Kannada. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .\nPROBLEM: Statement: ಒಂದು ವೇಳೆ ಗುಣಾತ್ಮಕ ಪ್ರತಿಕ್ರಿಯೆಯಿಂದಾಗಿ ಎಲ್ಲಾ ಹಸಿರುಮನೆ ಅನಿಲಗಳೂ ವಾತಾವರಣದೊಳಗೆ ಭಾಷ್ಪೀಭವನವಾಗುವಂತಾದರೆ, ಹತೋಟಿ ಮೀರಿದ ಹಸಿರುಮನೆ ಪರಿಣಾಮವು ಸಂಭವಿಸಬಹುದು.ಇಂಗಾಲದ ಡೈಆಕ್ಸೈಡ್ ಮತ್ತು ನೀರಿನ ಆವಿಯನ್ನು ಒಳಗೊಂಡ ಹತೋಟಿ ಮೀರಿದ ಹಸಿರುಮನೆ ಪರಿಣಾಮವು <MASK>ದಲ್ಲಿ ಸಂಭವಿಸಿರಬಹುದು.\n\n Option A: ಶುಕ್ರಗ್ರಹ\n\n Option B: ಶುಕ್ರ\n\n Option C: ಭೂಮಿ\n\n Option D: ಅಕೋಲ\n\nSOLUTION: ಶುಕ್ರಗ್ರಹ\n\nPROBLEM: Statement: ಕೇಳೆಕರ್ ಅವರು ೨೫ನೇ ಮಾರ್ಚ್ ೧೯೨೫ರಂದು ದಕ್ಷಿಣ <MASK>ದ ಕುನ್ಕೊಲಿಮ್ನಲ್ಲಿ ಜನಿಸಿದರು. ಅವರ ತಂದೆ ಡಾ.ರಾಜಾರಾಮ್ ಕೇಳೆಕರ್ ಒಬ್ಬ ವೈದ್ಯ. ನಂತರ ಅವರು ಭಗವದ್ಗೀತೆಯನ್ನು ಪೊರ್ಚುಗೀಸ್ ಭಾಷೆಗೆ ಅನುವಾದಿಸಿ ಪ್ರಸಿದ್ದರಾದರು. ರವೀಂದ್ರರವರು ಪಣಜಿಯ ಲೈಸಿಯಂ ಪ್ರೌಢಶಾಲೆಯ ವಿದ್ಯಾರ್ಥಿಯಾಗಿರುವಾಗಲೇ ೧೯೪೬ರ ಗೋವಾ ವಿಮೋಚನೆ ಚಳುವಳಿಯಲ್ಲಿ ಭಾಗವಹಿಸಿದ್ದರು. ಇದರಿಂದ ಅವರಿಗೆ ರಾಮ್ ಮನೋಹರ್ ಲೋಹಿಯರಂತಹ ರಾಷ್ಟ್ರನಾಯಕರೊಂದಿಗೆ ನಿಕಟ ಸಂಪರ್ಕ ಬೆಳೆಯಿತು. ಇಂಥ ನಾಯಕರ ಪ್ರಭಾವದ ಅಡಿಯಲ್ಲಿ ರವೀಂದ್ರರವರಿಗೆ ಸ್ಥಳೀಯ ಜನರನ್ನು ರಾಷ್ಟ್ರಿಯತೆಗಾಗಿ ಸಜ್ಜುಗೊಳಿಸುವಲ್ಲಿ ಭಾಷೆಯ ಪ್ರಾಮುಖ್ಯತೆಯನ್ನು ತಿಳಿಯುವಂತಾಯಿತು. ಮುಂದೆ ಅವರು ತಮ್ಮ ಮಾತೃಭಾಷೆಯಾದ ಕೊಂಕಣಿಯ ಶಕ್ತಿಯನ್ನು ಅರಿಯುತ್ತಾರೆ.\n\n Option A: ಭಾರತ\n\n Option B: ಗೋವಾ\n\n Option C: ಜಪಾನ್\n\n Option D: ದಿಲ್ಲಿ\n\nSOLUTION: ಗೋವಾ\n\nPROBLEM: Statement: ಭಾರತೀಯ ರಾಷ್ಟ್ರೀಯ ಕಾಂಗ್ರೆಸ್ ಮಂಡಿಸಿದ ನಿರ್ಣಯದ ಮೇರೆಗೆ, ಈ ಸ್ಥಳದಲ್ಲಿ ಒಂದು ಸ್ಮಾರಕವನ್ನು ನಿರ್ಮಿಸುವ ಸಲುವಾಗಿ <MASK>ರಲ್ಲಿ ಟ್ರಸ್ಟ್ ಒಂದನ್ನು ರಚಿಸಲಾಯಿತು. ೧೯೨೩ರಲ್ಲಿ ಇದಕ್ಕೆ ಬೇಕಾದ ಜಾಗವನ್ನು ಖರೀದಿಸಲಾಯಿತು. ಆ ಸ್ಥಳದಲ್ಲಿ ಸ್ಮಾರಕವನ್ನು ನಿರ್ಮಿಸಲಾಯಿತು. ಇದನ್ನು ೧೯೬೧, ಏಪ್ರಿಲ್ ೧೩ರಂದು, ಅಂದಿನ ಪ್ರಧಾನಿ ಜವಹರಲಾಲ್ ನೆಹರು ಮತ್ತಿತರ ಮುಖಂಡರ ಸಮ್ಮುಖದಲ್ಲಿ, ಭಾರತದ ಅಂದಿನ ರಾಷ್ಟ್ರಪತಿ ಡಾ.ರಾಜೇಂದ್ರ ಪ್ರಸಾದ್ ಅವರು ಉದ್ಘಾಟಿಸಿದರು.\n\n Option A: ೧೯೫೨\n\n Option B: ೧೯೨೦\n\n Option C: ಮಹಾಮಸ್ತಕಾಭಿಷೇಕಕ್ಕೆ\n\n Option D: ೧೯೪೦\n\nSOLUTION:",
"role": "user"
},
{
"content": "೧೯೨೦\n\n",
"role": "assistant"
}
] |
cot
|
cot_82340
|
[
{
"content": "Q: Given the sentence \"A drawing artist sitting down to eat at a cafe after a long day of hard work.\" can we conclude that \"The artist has food.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The artist has food due to a hard day of work.\nThe answer is yes.\n\nQ: Premise: \"A hiker jogs down a rocky road while blue skies and mountains cross the horizon.\"\nHypothesis: \"The person is indoors looking at tv.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: One cannot be indoors and jogging down a road or while outdoors.\nThe answer is no.\n\nQ: Can we conclude from \"A woman relaxes on the beach with her two dogs.\" that \"A woman relaxes on the beach.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The sentences parallel one another except for the mention of her pets. There is a woman on a beach in both.\nThe answer is yes.\n\nQ: Can we conclude from \"A tennis player in a blue shirt and white shorts lunges toward a tennis ball on a blue tennis court.\" that \"A player dives for the ball.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA:",
"role": "user"
},
{
"content": "Tennis player is a player and lunging toward a ball is the same as diving.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87494
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given four sentences of a story written in natural language. The given story is not complete and your job is to complete the story by selecting one of the end sentence choices from (A) and (B), such that the story does not sound complete and coherent, i.e., select an incorrect end sentence.\n\nSentence1: Rick grew up in a troubled household. Sentence2: He never found good support in family, and turned to gangs. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: The incident caused him to turn a new leaf. \n (A) He is happy now. (B) He joined a gang.\nSolution: B\nWhy? As mentioned in fourth sentence, the incident turned a new leaf to Rick's life; so, he must be happy now. Also, he was previously in gang, so, this incident cannot make him to join a gang. So, B is incorrect.\n\nNew input: Sentence1: I got into my car and closed the door. Sentence2: I turned the engine on and started to drive. Sentence3: I was headed in the direction of the gas station. Sentence4: It was lunch time and I was starting to get hungry. \n (A) I decided to buy chips at the gas station. (B) I decided to never eat again.\nSolution:",
"role": "user"
},
{
"content": "B",
"role": "assistant"
}
] |
cot
|
cot_71936
|
[
{
"content": "Q: Can we conclude from \"Two very friends lost in the middle of the desert with nothing but a portable black mattress and a book with maps.\" that \"Two people wonder in a desert.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The two people are friends and they are lost in a desert.\nThe answer is yes.\nQUESTION: Test for natural language inference.\nPremise: \"A guy is riding his bike next to a brick building with bright blue doors.\"\nHypothesis: \"A man is riding his bike to work.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: A man riding his bike is not necessarily riding his bike to work.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"Five white dogs with muzzles are running towards the camera.\" is it true that \"Dogs are running outside.\"?\nThe dogs could be running inside a building instead of running outside.\nThe answer is it is not possible to tell.\nQ: Can we conclude from \"A group of men standing near a work truck.\" that \"The men are waiting for work.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Men standing near a work truck are not necessarily waiting for work.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A group of children stand underneath some banners.\" is it true that \"Stretching their arms over their heads.\"?\n\nLet's solve it slowly: A group of kids with their hands raised in the air.\nThe answer is yes.\nQUESTION: If \"Two workers in protective suits cut into a metal barrel while onlookers observe their performance.\" does that mean that \"The workers are going to turn a barrel into a bar-b-que pit.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "The workers could or couldn't be going to trun the barrel into a bar-b-que pit.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84833
|
[
{
"content": "In this task, you are given an input i,A where i is an integer and A is an array. You need to find every ith element of A starting with the 1st element.\n\n[Q]: 8, ['9257', 'U', 'd', '1913', 'i', 'K', '937', 'h', 'a', '9193', 'm', '9383', '4847', '6265', 'm', 'W', 'G', 'Q', '7147', 'y', '7869', 'W', '1769', '9747', '6663', '5649', 'C', 's', '6093', 'S', 'P', '6233', '6453', 'i', 'E', 'S', '17', 'q', 'G', '4385', 'C', 'Q', '1477', 'G', '2953', 'm', '6283', '8223', 'Q']\n[A]: 9257, a, G, 6663, 6453, C, Q\n\n\n[Q]: 2, ['o', '2869', '5133', 'S', 'c', 'O', '8133', '2645', 'z', '5975', 'h', 'i', '3609', 'P', '4767', 'S', 'a', '395', 'L', '2151', '3991', '943', 'M', 'M', 'V', '7379', 'p', '2093', 'J', 'M', 'A', '3209', '4049', '621']\n[A]: o, 5133, c, 8133, z, h, 3609, 4767, a, L, 3991, M, V, p, J, A, 4049\n\n\n[Q]: 5, ['443', 'w', '9', 'f', 'J', 'c', '3967', '529', 'Y', '5289', '173', 'F', 'a', '3943', 'Q', 'Q', '3225', 'n', '3859', 'e']\n[A]:",
"role": "user"
},
{
"content": "443, c, 173, Q\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84501
|
[
{
"content": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\nQ: 5, 13, ['B', 'R', '6213', '9839', '6611', 'J', '9323', '8111', '9733', 'v', '129', '7023', '8583', '1115', 'I']\n\nA: 6611, J, 9323, 8111, 9733, v, 129, 7023, 8583\n****\nQ: 2, 5, ['5579', '4291', '1649', 'S', 'w', '3039', '3373', '1317', 'B', 'r', 'G', '6551', '6263', '643', '2453', 'r']\n\nA: 4291, 1649, S, w\n****\nQ: 7, 22, ['3361', 'Y', '6803', 'H', '6551', 'G', 'h', '4953', '2563', 'j', 'C', '7503', 'N', '655', 'R', 'D', 'y', 'u', 'V', 'c', '7167', '3923', '9759', '1865']\n\nA:",
"role": "user"
},
{
"content": "h, 4953, 2563, j, C, 7503, N, 655, R, D, y, u, V, c, 7167, 3923\n****\n",
"role": "assistant"
}
] |
cot
|
cot_52921
|
[
{
"content": "Q: Premise: \"Several people standing at a stoplight waiting to cross the street.\"\nHypothesis: \"People wait to cross the street.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: yes\nCoT: The people want to cross the street because they are waiting at the stoplight.\n****\nQ: Given the sentence \"A girl in a pink suit chases a gull on a beach.\" can we conclude that \"There is a bird on the beach.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: yes\nCoT: A gull is a bird and the sentence states that said bird is on a beach.\n****\nQ: Can we conclude from \"A man in brown jacket and blue cap is washing a black jacket in fountain.\" that \"A man in jacket and blue cap is washing a black jacket in fountain.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: yes\nCoT: A man wearing a jacket and a blue cap is washing a black jacket in the fountain is a simplification of a man wearing a brown jacket and a blue cap washing a jacket in the fountain.\n****\nQ: Can we conclude from \"A boy with a blue mohawk plays the violin.\" that \"A boy with a red mohawk is playing a piano.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: no\nCoT:",
"role": "user"
},
{
"content": "A red Mohawk is different from a blue Mohawk and a piano is different from a violin.\n****",
"role": "assistant"
}
] |
cot
|
cot_51298
|
[
{
"content": "QUESTION: Can we conclude from \"A band that is playing outside for a benefit in new york.\" that \"A group of musicians perfoms in a large city.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: The musicians are in a large city because they are in New York.\nThe answer is yes.\n[QUESTION] Can we conclude from \"Workers in orange suits are working on a road.\" that \"There are workers in orange suits.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nThere are workers in orange suits means the same as workers in orange suits.\nThe answer is yes.\nQ: Premise: \"A man inspecting crops in a middle eastern town.\"\nHypothesis: \"A man trying to analyse the kind of crop he has in his hand.\"\nDo we know that the hypothesis entailed by the premise?\nA: A man inspecting crops does not imply the man is trying to analyse the kind of crop he has.\nThe answer is it is not possible to tell.\nQUESTION: If \"The tourists are out on the river in italy.\" does that mean that \"The man in the black and white striped shirt will tell them about the seine.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The tourists are in Venice while a man in a striped shirt tells them about the seine.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"A dog has his paw on the red roof of a kennel.\" can we conclude that \"A dog is in the kennel.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nIf a dog has his paw on the red roof this does not mean he is in the kennel.\nThe answer is it is not possible to tell.\nQ: Test for natural language inference.\nPremise: \"Woman sculpting gingerbread house.\"\nHypothesis: \"A woman is sculpting a marble statue.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA:",
"role": "user"
},
{
"content": "A gingerbread house and a marble statue cannot be sculpted at the same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82365
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\n\nEx Input:\n['w', '469', 'B', '6413', '5665', 'g', 'W', '889', 'z', 'v', '3571', 'J', '535', '9703', 'L', 'u', 'p', '6097', 'a', '8067', 'G', '8749', 'B', 'h', 'q', 'a', '7959', '1777', 'N', 'Q', '8079', '6871', '9313', 'M', '4455', 'f']\n\nEx Output:\n1, 3, 6, 7, 9, 10, 12, 15, 16, 17, 19, 21, 23, 24, 25, 26, 29, 30, 34, 36\n\n\nEx Input:\n['s', '5037', '6039', '1609', '6759', '9771', 'e', 'X', 'm', 'S', 'g', '9741']\n\nEx Output:\n1, 7, 8, 9, 10, 11\n\n\nEx Input:\n['5059', 'X', 'o', 'L', '5663', 'e', '3413', '7627', '3163']\n\nEx Output:\n",
"role": "user"
},
{
"content": "2, 3, 4, 6\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86974
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a trivia question, classify broad topical category from this list: 'theater', 'geology', 'book', 'tv', 'astronomy', 'aviation', 'military', 'government', 'boxing', 'projects', 'metropolitan_transit', 'law', 'venture_capital', 'broadcast', 'biology', 'people', 'influence', 'baseball', 'spaceflight', 'media_common', 'cvg', 'opera', 'olympics', 'chemistry', 'visual_art', 'conferences', 'sports', 'language', 'travel', 'location', 'award', 'dining', 'martial_arts', 'comic_strips', 'computer', 'user', 'tennis', 'music', 'organization', 'food', 'event', 'transportation', 'fictional_universe', 'measurement_unit', 'meteorology', 'distilled_spirits', 'symbols', 'architecture', 'freebase', 'internet', 'fashion', 'boats', 'cricket', 'film', 'medicine', 'finance', 'comic_books', 'celebrities', 'soccer', 'games', 'time', 'geography', 'interests', 'common', 'base', 'business', 'periodicals', 'royalty', 'education', 'type', 'religion', 'automotive', 'exhibitions'.\n\nWhat country has borders with Libya, Sudan and Israel?\nSolution: location\nWhy? This question is about a physical place, so is classified as 'location'\n\nNew input: Which TV Game Show has been presented by Leslie Crowther, Bruce Forsyth and Joe Pasquale?\nSolution:",
"role": "user"
},
{
"content": "tv",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91205
|
[
{
"content": "In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.\n--------\nQuestion: ['s', '6723', 'l', '1573', '1129', 'n', '4277', '5003', 'y', '7563', 'c', '6747', '3105', 's', '3593', '8417', '8253', '4157', 'w', 'f', 'z', 'd', '9685', '1033', 'h', '4893', 't', 'j', '6821', 'z', 'a', 'u', '591', 'o', '1087', '2147', '1223', '2339', 'i', 'y', '9307', 'x', 'z', 'r', 'y']\n\nAnswer: a, c, d, f, h, i, j, l, n, o, r, s, t, u, w, x, y, z\n\n\nQuestion: ['y', 'p', 'q', '2157', 'b', 'w', '8875', 'k', 'i', 'd', '9743', '4941', 'b', 'p', '9941', '495', 'h', 'i', '839', 'c', 'h', 'f', 'b', 'a', 'k', 'z', '7549', '4149', 'h', 'j', '1947', 't', 'f', 'c', '1243']\n\nAnswer: a, b, c, d, f, h, i, j, k, p, q, t, w, y, z\n\n\nQuestion: ['r', 'g', 'u', 'f', '1239', 'j', '9427', '4169', '5453', '7409', 's', 'h', '3975', '9277', 'u', 'a', '5853', '6191', 'o', '549', 'f', 'r', '8063', '2391', '6741', '5845', '6951', 'o', 'k', 'y', '5869', '797', '2615', '7221']\n\nAnswer:",
"role": "user"
},
{
"content": "a, f, g, h, j, k, o, r, s, u, y\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82744
|
[
{
"content": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n[EX Q]: 14, 15, ['Q', '2131', 'X', 'u', 'y', '9699', '7305', '3017', '8151', 'X', '9723', '7907', 'j', '1527', 'u', 'D', 'b', '7735', '1713']\n[EX A]: 1527\n\n[EX Q]: 7, 17, ['149', 'O', 'h', '7873', '9227', '5655', '8945', 'I', 'c', 'V', 'Z', 'I', 'L', '1153', 'L', 'Y', '2031', 'B', 'S', 'x', 'u', '2483', 'M', '2469', '4991']\n[EX A]: 12129\n\n[EX Q]: 1, 2, ['4743', '1157', '4093']\n[EX A]:",
"role": "user"
},
{
"content": "5900\n\n",
"role": "assistant"
}
] |
cot
|
cot_90160
|
[
{
"content": "QUESTION: Given the sentence \"A group of females running a marathon.\" can we conclude that \"A group of women running.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Women is a synonym of females and both are running in a group.\nThe answer is yes.\n[QUESTION] Premise: \"A surfer in a dark wetsuit carries a white surfboard towards the ocean.\"\nHypothesis: \"A surfer exits the ocean with his blue surfboard.\"\nDo we know that the hypothesis entailed by the premise?\nA person who exits the ocean would be walking away from the ocean not towards the ocean.\nThe answer is no.\nQ: If \"A group of people painting the side of a building in an array of colors.\" does that mean that \"They are painting each other naked.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The people are painting a side of a building and not each other.\nThe answer is no.\nQUESTION: Premise: \"A man in a harness wearing a white hat climbing down a waterfall.\"\nHypothesis: \"A geologist is exploring a waterfall.\"\nDo we know that the hypothesis entailed by the premise?\n\nLet's solve it slowly: Because a man is climbing down a waterfall doesn't mean is a geologist.\nThe answer is it is not possible to tell.\n[QUESTION] Can we conclude from \"People gather to watch a street performer.\" that \"The people are riding a rollercoaster.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nPeople that gather to watch a street performer cannot be the ones riding a rollercoaster.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A man sits in a chair with a fishing pole next to water.\"\nHypothesis: \"A man sits next to the water daydreaming.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA:",
"role": "user"
},
{
"content": "It's unclear whether it's the man or the fishing pole that's exactly next to the water.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_95833
|
[
{
"content": "QUESTION: Given the sentence \"A group of females running a marathon.\" can we conclude that \"A group of women running.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Women is a synonym of females and both are running in a group.\nThe answer is yes.\n[QUESTION] Premise: \"A surfer in a dark wetsuit carries a white surfboard towards the ocean.\"\nHypothesis: \"A surfer exits the ocean with his blue surfboard.\"\nDo we know that the hypothesis entailed by the premise?\nA person who exits the ocean would be walking away from the ocean not towards the ocean.\nThe answer is no.\nQ: If \"A group of people painting the side of a building in an array of colors.\" does that mean that \"They are painting each other naked.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The people are painting a side of a building and not each other.\nThe answer is no.\nQUESTION: Premise: \"A man in a harness wearing a white hat climbing down a waterfall.\"\nHypothesis: \"A geologist is exploring a waterfall.\"\nDo we know that the hypothesis entailed by the premise?\n\nLet's solve it slowly: Because a man is climbing down a waterfall doesn't mean is a geologist.\nThe answer is it is not possible to tell.\n[QUESTION] Can we conclude from \"People gather to watch a street performer.\" that \"The people are riding a rollercoaster.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nPeople that gather to watch a street performer cannot be the ones riding a rollercoaster.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A man sits in a chair with a fishing pole next to water.\"\nHypothesis: \"A man sits next to the water daydreaming.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA:",
"role": "user"
},
{
"content": "It's unclear whether it's the man or the fishing pole that's exactly next to the water.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91266
|
[
{
"content": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given a candidate for the second sentence and you need to identify if the given sentence connects the first sentence with the rest of the story. Indicate your answer by \"Yes\" if it connects, otherwise \"No\". Do not generate anything else apart from \"Yes\" or \"No\". The given sentence is incorrect if it changes the subsequent storyline, so that at least one of the three subsequent sentences form a consistent story.\n\nEx Input:\nSentence 1: Beth had just moved to a new town. \n Sentence 3: She wondered if she would make any friends \n Sentence 4: Then her neighbors came over to introduce themselves \n Sentence 5: Beth realized she already had several built-in friends! \n Given Sentence 2: She was very nervous.\n\nEx Output:\nNo\n\n\nEx Input:\nSentence 1: Tom loved serving fancy treats. \n Sentence 3: He carefully sliced some cheese \n Sentence 4: He put them on a plate and served them \n Sentence 5: His guests were very impressed \n Given Sentence 2: He bought a cheese slicer for a party he was hosting.\n\nEx Output:\nYes\n\n\nEx Input:\nSentence 1: The Waltons lost their house in a storm last month. \n Sentence 3: Most of the family didn't want to live in a stormy area anymore \n Sentence 4: So they bought a new home elsewhere \n Sentence 5: Now they feel more safe and secure \n Given Sentence 2: The recipe said to add the lemon zest to them.\n\nEx Output:\n",
"role": "user"
},
{
"content": "No\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_64916
|
[
{
"content": "The man who is sitting has a suit on with a read shirt.\nThe question and answer are below.\nGiven the sentence \"A man sits on a train with a suit and red shirt.\" can we conclude that \"A man is sitting.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nyes\n\nThe boy is about to throw the ball back into play.\nThe question and answer are below.\nIf \"A young boy in a red jersey jumps.\" does that mean that \"About to throw a basketball in front of a crowd.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nit is not possible to tell\n\nJust because A group of people holding red flags and pamphlets in front of a large building does not indicate that A group is protesting a company.. So what could be the question?\nQuestion followed by answer: Premise: \"A group of people holding red flags and pamphlets in front of a large building.\"\nHypothesis: \"A group is protesting a company.\"\nDo we know that the hypothesis entailed by the premise?\nit is not possible to tell\n\nThe dog would not simultaneously hate balls and also run with a ball in its mouth.\nThe question and answer are below.\nPremise: \"A black dog runs through the water with a ball in its mouth.\"\nBased on this premise, can we conclude that the hypothesis \"Dogs hate balls.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nno\n\nOne can be looking either forward or at one's smashed car.\nThe question and answer are below.\nTest for natural language inference.\nPremise: \"A woman in gray looking forward.\"\nHypothesis: \"The lady is looking at her smashed car.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nno\n\nOne can not sleep in a bed if people are jumping on the bed.\nThe question and answer are below.\n",
"role": "user"
},
{
"content": "Can we conclude from \"Two men sleep in a bed in a store while children look on.\" that \"The children are jumping on the bed.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nno",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_90305
|
[
{
"content": "Teacher: In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nSentence 1: The cashier was counting the dollar bills at her desk. \n Sentence 3: Everyone panicked and started to scream. \n Sentence 4: The men threatened the people to remain quiet. \n Sentence 5: The cashier handed them the cash so they would go away. \n Option 1: Two men rushed into the store and held their guns up. \n Option 2: Two dogs rushed into the store.\nSolution: Option 1\nReason: Option 1 forms a consistent story with the given four sentences. In constrast, Option 2 is incorrect as the entty 'two dogs' is not consistent with 'men' mentioned in Sentence 4.\n\nNow, solve this instance: Sentence 1: I really wanted some chicken wings. \n Sentence 3: Alas, they tasted terrible \n Sentence 4: I decided to order some wings for takeout \n Sentence 5: They were incredibly tasty! \n Option 1: I decided to make some frog legs instead. \n Option 2: I decided to make some.\nStudent:",
"role": "user"
},
{
"content": "Option 2",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91255
|
[
{
"content": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\n\nExample Input: ['8763', 'k', 'k', '2827', '8269', 'T', '3961', '6589', '4817', '2701']\nExample Output: 8763, 11, 11, 2827, 8269, 20, 3961, 6589, 4817, 2701\n\nExample Input: ['h', 'v', 'j', 'O', 'N', 'J', '7149', '2651', '4951', '2217', 'O', '6331', '7163', '1447', '5935', '1697', 'P', 'K', '7253', '6223', 't', 's', 'F', 'c', 'c', 'M', 'f', '5945', '2289', 'g', '585', '2831', '3187', '2299', 'y', '151']\nExample Output: 8, 22, 10, 15, 14, 10, 7149, 2651, 4951, 2217, 15, 6331, 7163, 1447, 5935, 1697, 16, 11, 7253, 6223, 20, 19, 6, 3, 3, 13, 6, 5945, 2289, 7, 585, 2831, 3187, 2299, 25, 151\n\nExample Input: ['C', '4621', 'I', 'J', 'p', 'M', 'E', '5019', '8205', '6069', '8203', '8973', 'a', 's']\nExample Output:",
"role": "user"
},
{
"content": "3, 4621, 9, 10, 16, 13, 5, 5019, 8205, 6069, 8203, 8973, 1, 19\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_90118
|
[
{
"content": "In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\n\nQ: Title: Jake never worried about his phone's battery status. A potential employer called before Jeff bothered to charge his phone. Jeff now understands the value of keeping a charged phone. Choices: a. Maggy smells the smoke and goes to get the pizza out. b. Being unemployed, he was trying to find a good job. c. While out with friends, his phone died, as usual.\n\nA: bc\n****\nQ: Title: The concert had been sold out for weeks. One of his friends had tickets to the concert. Justin's friend found out he had to work the night of the concert. Choices: a. Justin was able to buy his friend's tickets. b. Justin wanted tickets to see his favorite band. c. They had a lot of fun playing in the water!\n\nA: ab\n****\nQ: Title: They wanted a table for their kitchen most of all. They bought it and brought it home. It was a great addition to their home! Choices: a. The family wanted some new furniture. b. Tom accomplished his goal of voting. c. They found a beautiful table in a local store.\n\nA:",
"role": "user"
},
{
"content": "ac\n****\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_85924
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the numerical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no numerical element is in the list.\n\nInput: Consider Input: ['593', 'r', '1863', '7529', '3187', 'v', 'G', '1081', '101', 'c', 'v', '8419', '707', 'w', 'M', '1871', '1379', 'V', '7567', 'T', 'E', 'w', '7391']\n\nOutput: 1, 3, 4, 5, 8, 9, 12, 13, 16, 17, 19, 23\n\n\nInput: Consider Input: ['r', 'k', 'P', '615', 'U', '43', '9647', 'N', '3729', '3803', 'j', '327', '8973', '5953', '1421', '5013']\n\nOutput: 4, 6, 7, 9, 10, 12, 13, 14, 15, 16\n\n\nInput: Consider Input: ['C', '6979', '2437', '8395', 's', '7407', '245', '2197', 'k', '7051', 'b', 'B', '1555', '8557', 'h']\n\n",
"role": "user"
},
{
"content": "Output: 2, 3, 4, 6, 7, 8, 10, 13, 14\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86549
|
[
{
"content": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\n\nInput: Consider Input: 7, ['4871', '3897', 'B', 't', 'V', '7127', '8163', 'R', 'c', 'o', 'w', 'b', '9099', '1405', 'i', '8279', '3689', 'x']\n\nOutput: 4871, 3897, B, t, V, 7127, 8163, R, c, o, w\n\n\nInput: Consider Input: 4, ['971', '3213', 'E', 'o', 'x', 'h', '5493', '4229']\n\nOutput: 971, 3213, E, o\n\n\nInput: Consider Input: 7, ['673', 's', 'f', 'J', '2605', '5311', 'p', '4403', 'K', 'I', 'e', '7665', 'G', '5787', 'S', '3589', '8205', '5545', 'T', '9189', 'N', '3577', '7509', 'k', '657', '2725', 'i', '4687', 'L']\n\n",
"role": "user"
},
{
"content": "Output: 673, s, f, J, 2605, 5311, p, 4403, K, I, e, 7665, G, 5787, S, 3589, 8205, 5545, T, 9189, N, 3577\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_63973
|
[
{
"content": "Question and answer: Q: Can we conclude from \"A woman in a red sweater and a girl is in front of a girl in a green hoodie& a girl with a brown jacket and pink purse.\" that \"The three women are all related.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: it is not possible to tell\nExplanation: All of these females could be standing in line but nothing in the sentence tells us that they are related to one another.\n\n\nQuestion and answer: Q: Can we conclude from \"A large group of people stands on line to order at a fast food restaurant.\" that \"A group of people stand in a line.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: yes\nExplanation: The size and location of the group are irrelevant to the fact that a group of people is standing in/on (the two words are synonymous in this context) line.\n\n\nQuestion and answer: Q: Premise: \"People sitting on what looks like a train car with bar-covered windows that has some kind of arabic writing above one window.\"\nBased on this premise, can we conclude that the hypothesis \"People sat on a vehicle looking object with arabic on one of the windows.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: it is not possible to tell\nExplanation:",
"role": "user"
},
{
"content": "People sitting on what looks like a train car with bar-covered windows that has some kind of Arabic writing above one window does not imply that they sat on a vehicle looking object with Arabic on one of the windows.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91675
|
[
{
"content": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given a candidate for the second sentence and you need to identify if the given sentence connects the first sentence with the rest of the story. Indicate your answer by \"Yes\" if it connects, otherwise \"No\". Do not generate anything else apart from \"Yes\" or \"No\". The given sentence is incorrect if it changes the subsequent storyline, so that at least one of the three subsequent sentences form a consistent story.\n\nQ: Sentence 1: I thought I had a right to own a gun. \n Sentence 3: The police found my gun and gave me a ticket \n Sentence 4: I researched a citizen's right to own a gun \n Sentence 5: I learned I can own a gun but I need a permit for it \n Given Sentence 2: Her brother Cam wanted to watch a baseball game.\n\nA: No\n****\nQ: Sentence 1: Scott rubbed the sleep from his eyes. \n Sentence 3: Time to get up and let the dog out \n Sentence 4: Tom's foot felt a squishy sensation when it met the floor \n Sentence 5: It was already too late to let the dog out to poop \n Given Sentence 2: His dad said Jimmy needed to dig for worms before the fishing trip.\n\nA: No\n****\nQ: Sentence 1: Sarah couldn't squeeze another hanger in her closet. \n Sentence 3: She got some free boxes from the liquor store in town \n Sentence 4: Everything she no longer needed got folded and placed in the boxes \n Sentence 5: When she was done, she donated everything and felt great \n Given Sentence 2: She decided it was a good time to get rid of a lot of things.\n\nA:",
"role": "user"
},
{
"content": "Yes\n****\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_83754
|
[
{
"content": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given a candidate for the second sentence and you need to identify if the given sentence connects the first sentence with the rest of the story. Indicate your answer by \"Yes\" if it connects, otherwise \"No\". Do not generate anything else apart from \"Yes\" or \"No\". The given sentence is incorrect if it changes the subsequent storyline, so that at least one of the three subsequent sentences form a consistent story.\n\nExample Input: Sentence 1: Tori wanted to make a new skirt. \n Sentence 3: She picked out the perfect thread \n Sentence 4: She sat down in front of a sewing machine, ready to work \n Sentence 5: Suddenly, she realized she did not know how to sew at all \n Given Sentence 2: His mother asked her to bring cranberry sauce.\nExample Output: No\n\nExample Input: Sentence 1: My wife babysat her 22 month old grandnephew Timmy today. \n Sentence 3: She gave him her sunglasses to play with \n Sentence 4: Timmy broke her sunglasses \n Sentence 5: Luckily it was a cheap pair \n Given Sentence 2: He bought a new scale for his home.\nExample Output: No\n\nExample Input: Sentence 1: Dan found out his dad was moving. \n Sentence 3: He decided to run away \n Sentence 4: His mom could not find him anywhere \n Sentence 5: Dan finally came home and was ground for 6 weeks \n Given Sentence 2: And he noticed that there was nothing to watch but children's shows.\nExample Output:",
"role": "user"
},
{
"content": "No\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82015
|
[
{
"content": "In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.\n\nInput: Consider Input: Title: The Dead Bug. Sentence 1: Paul saw something floating in his soup. Sentence 2: It was a disgusting dead bug! Sentence 3: Paul screamed and called for a waiter. Sentence 4: The waiter took the bowl away. Choices: a. He apologized and paid for the meal. b. He then landed the plane without injury to any passengers.\n\nOutput: b\n\n\nInput: Consider Input: Title: The Sprinkler. Sentence 1: A father and his daughter were walking to school one morning. Sentence 2: Their journey took them past many houses with pretty front yards. Sentence 3: They stopped to look at some nice flowers in one of the yards. Sentence 4: Suddenly a sprinkler came on and soaked them both! Choices: a. She used it every day. b. They had to turn back and dry off at home before heading out again!\n\nOutput: a\n\n\nInput: Consider Input: Title: The Lost Compass. Sentence 1: Laura had a precious compass her grandfather gave her. Sentence 2: It was her favorite possession. Sentence 3: One day on a school field trip, she lost the compass. Sentence 4: Laura cried and cried when she realized it was not in her pocket. Choices: a. The waitress came over to take her order. b. The next day, the compass was found and returned safely to her.\n\n",
"role": "user"
},
{
"content": "Output: a\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87032
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\n\nExample Input: ['w', '6085', 'C', 'F', 'L', 'F', '4663', 's', 'Y', '1613', '97', '127', 'a', 'h', 'p', '6251']\nExample Output: 1, 3, 4, 5, 6, 8, 9, 13, 14, 15\n\nExample Input: ['5777', 't', 't', '4549', '3559', '4305', '6369', 'r', 'd', 'J', '5213', 'E', 'G', '8025', 'u', 'P', '1473', '6451', '4073', '8777', 'P', '9345', 'J', '1145', 'T', '7677', 'a', 'K', '3641', 's', 'J', 'k', '7663', 'X', 'o', 'z', 'm', 'Q', 't', '7999']\nExample Output: 2, 3, 8, 9, 10, 12, 13, 15, 16, 21, 23, 25, 27, 28, 30, 31, 32, 34, 35, 36, 37, 38, 39\n\nExample Input: ['5681', '1237', 'v', 'C', 'K', '4111', 'm', '7787', 'h', '8951', 'h', '7075', 'I', '6465', 'Z', 'd', 'l', '1217', 'k', 'T', '5863', '3391', 'Z', 'a', '4105']\nExample Output:",
"role": "user"
},
{
"content": "3, 4, 5, 7, 9, 11, 13, 15, 16, 17, 19, 20, 23, 24\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_75427
|
[
{
"content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\n\nText: this happened about 3 hours ago ... well here goes.\n\ni have been abroad in england for about 3 months now, which means i'm not really up to date what goes on at home, evenso i do have a quick glance over facebook about once a week, but really, who still uses facebook to communicate.\n\nwell apparently my brother does (with whom i am not been on speaking terms for the better of half a year), to plan a party for his best friend. i saw that i've had been invited into a group by him, but didn't really care as it came from him. \n\nour circle of friends is pretty much identical, so i'm in touch with some of them via whatsapp, from which i gathered they are all going to a party this weekende.\n\nnow, my daily life here is something like this, work work work --> pub, i'm quite the wodka man but not much when it comes to beer, so i'm frequently hungover. well today i got a message from said best friend, we chit chat for some time and to end the conversation i wish him fun at the party on saturday.\n\nwhich i didn't realise is that he never told me anything about a party, so there i went and spoiled three months of planing in the matter of 10 minutes.\nOutput:",
"role": "user"
},
{
"content": "TIFU by spoiling a surprise party, which was 2 month in planing.",
"role": "assistant"
}
] |
cot
|
cot_60794
|
[
{
"content": "QUESTION: Given the sentence \"A woman is hauling up a bucket or bottle using a rope which is suspended from a window.\" is it true that \"A woman carrying clean water to take a shower.\"?\n\nLet's solve it slowly: Taking a shower is only one thing clean water can be used for.\nThe answer is it is not possible to tell.\n[QUESTION] Can we conclude from \"Two people in the water while two other people are jumping out of the water.\" that \"The people are playing in and out of the water.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nTwo people and two other people can be commonly referred to as the people.\nThe answer is yes.\nQ: Test for natural language inference.\nPremise: \"Here are some elderly people sitting on the bench in the park.\"\nHypothesis: \"Some elderly people are wearing hats on a bench.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Elderly people sitting on a bench in a park may or may not be wearing hats.\nThe answer is it is not possible to tell.\nQUESTION: If \"A black-haired girl is eating corn on the cob.\" does that mean that \"The corn got stuck in the black-haired girls teeth.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Eating corn on the cob does not imply corn got stuck in teeth.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"A man in a gray shirt and a hat holding a jackhammer.\" is it true that \"A man holds a jackhammer.\"?\nA man holds a jackhammer wear in a gray shirt and a hat.\nThe answer is yes.\nQ: Test for natural language inference.\nPremise: \"Three adults and three children are swimming in a public pool with one child ready to dive.\"\nHypothesis: \"A group of people are at the neighborhood pool party.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA:",
"role": "user"
},
{
"content": "Swimming a a public pool would not always be a neighborhood pool party.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_79659
|
[
{
"content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nselect the rows whose player record fuzzily matches to david giménez . take the total g record of this row . select the rows whose player record fuzzily matches to casado . take the total g record of this row . the first record is greater than the second record .\nOutput:",
"role": "user"
},
{
"content": "greater { hop { filter_eq { all_rows ; player ; david giménez } ; total g } ; hop { filter_eq { all_rows ; player ; casado } ; total g } }",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_72163
|
[
{
"content": "Detailed Instructions: In this task, you are given a Reddit post as a text. Your task is to generate a short summary for this text. The summary must include a situation which caused humor. The summary should be one or two sentences long.\nQ: Text: so first post ever, i thought i would share this with you guys, here it goes.\n\nthis didn't happen today but i figured that would be okay. i'm in a branch of military service and it had been some time since i'd been home and for those of you who don't know on government holidays most of us get the day off so we get an extended weekend. so i traveled all the way home and didn't arrive until around 5:00 am so i immediately went to sleep. my girlfriend and i had planned out that she would come wake me early in the morning and well... as a 19 year old guy who hasn't gotten laid in a while was pretty horny. \n\nshe texted me as soon as she left and it woke me up and i couldn't sleep anymore from the excitement. i wont go into too much detail because i'm not sure if i should or not but anyways she came straight into my room and we start going at for a while and things are going smooth and i'm doing all my favorite positions. i decide to be the big spoon and keep going, all of a sudden a hear a knock on the door and pull the blanket over us and i'm still inside.\n\nfrom my grandmothers perspective it would have seemed like i just wasn't wearing a shirt (being fully naked) and my girlfriend was fully dressed (with her pants off). anyways my grandmother walks in and doesn't expect a thing we just both smile and say hi innocently like we weren't in the middle of having sex. my grandmother pulls out her new camera and snaps a picture of us laying in bed... i was absolutely mortified. i can imagine looking in photo albums years from now and seeing our shame and sweat...\n\nand that's that. now it seems pretty funny my girlfriend is still super embarrassed. \n\n \n\nedit: so for everyone asking did i finish? of course i did. also a big thank you i'm glad a lot of you liked my story and i really appreciate the advice i'll try to incorporate all of your tips into any, if at all, future stories.\noh, also its not like my grandmother let us do what ever we wanted, we've just been together for 3 years now and me being gone so frequently doesn't permit us to be together much, so my grandmother doesn't mind when we lay down together. \n\np.s. i'll think about rewording the title next time... gross but hilarious you dyslexic folk.\nA:",
"role": "user"
},
{
"content": "went home to visit girlfriend, grandma unknowingly took picture of me and my girl friend having sex",
"role": "assistant"
}
] |
cot
|
cot_62477
|
[
{
"content": "Q: Can we conclude from \"A black lady with an orange vest is handing back a card through a checkout window.\" that \"The checkout window is closed.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The woman would not be handing back a card through a checkout window if the window were closed.\nThe answer is no.\nQUESTION: Test for natural language inference.\nPremise: \"A man and a boy each grasp a small black bag in their outstretched arms.\"\nHypothesis: \"Group try to hold a iron rod.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: Small black bag and a iron rod are not the same.\nThe answer is no.\n[QUESTION] If \"A boy in a green and yellow t-shirt is playing a guitar in a large crowd.\" does that mean that \"The boy in green is wearing jeans.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA boy wearing a green and yellow t-shirt is not always wearing jeans.\nThe answer is it is not possible to tell.\nQ: Given the sentence \"A brown dog is trying to catch a flying disk but missed it.\" is it true that \"The dog is drinking from his dish.\"?\nA: A dog who is drinking from a dish cannot simultaneously be trying to catch a flying disk.\nThe answer is no.\nQUESTION: Given the sentence \"Two policemen standing in a parking lot.\" can we conclude that \"The donut shop banned the cops.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The donut shop banned the cops would happen when they were inside the donut shop and would not happen when they were standing in a parking lot.\nThe answer is no.\nQUESTION: Can we conclude from \"Man plays fetch with his dog near a boat dock.\" that \"A woman plays with her cat.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "A woman can not play with her cat when its a man playing with his dog.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_74937
|
[
{
"content": "Instructions: In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\nInput: Context Word: insulin. \nQuestion: Jane had a hard time giving her cat insulin unlike giving it a pill because the _ took two people. \nAnswer: insulin.\nOutput:",
"role": "user"
},
{
"content": "Jane had a hard time giving her cat insulin unlike giving it a pill because the _ took one person.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89925
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given an article, a question which often contains a blank and four options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer (from the given options) for the question from the given article and return one of the options from \"A\", \"B\", \"C\", and \"D\". Do not generate anything else apart from one of the following characters: \"A\", \"B\", \"C\", \"D\". There is only one correct answer for each question.\n\nArticle: Homework can put you in a bad mood , and that might actually be a good thing. Researchers from the University of Plymouth in England doubted whether mood might affect the way kids learn. To find out the answer, they did two experiments with children. The first experiment tested 30 kids. Someshapes were hidden inside a different, larger picture. The kids had to find the small shapes while sitting in a room with either cheerful or sad music playing in the background. To test their mood, the scientists asked the kids to point to one of five faces, from happy to sad. Children who listened to cheerful music tended to point to the smiley faces while the others pointed to the unhappy ones. The researchers found that sad kids took at least a second less to find the small shapes. They also found an average of three or four more shapes. In the second experiment, 61 children watched one of two scenes from a film. One scene was happy, and the other was sad. Just like in the first experiment, kids who saw the sad scene acted better compared to the others. The researchers guessed that feeling down makes people more likely to focus on a problem or difficult situation. Not all scientists agree with them, however. Other studies argued that maybe, that cheerful music in the first experiment distracted kids from finding shapes. While scientists work on finding out the answers, it still might be wise to choose when to do your tasks according to your mood. After eating a delicious ice cream, for example, write an essay. \n Question: Researchers did experiments on kids in order to find out _ . \n Options: (A) how they really feel when they are learning (B) whether mood affects their learning ability (C) what methods are easy for kids to learn (D) the relationship between sadness and happiness\nSolution: B\nWhy? It is clearly mentioned in the article that to the check effect of mood on children is the main purpose of the experiment. So, B is the correct answer.\n\nNew input: Article: As many as 4 out of every 1,000 infants born today have permanent hearing loss. When parents learn that their child has hearing loss, they are faced with many difficult decisions. These decisions can include choosing therapies and schools, as well as finding financial help for hearing aids or cochlear implants . Help Me Hear Foundation is a public charity that gives the gift of hearing to deaf children from families existing on very low incomes around the world. Help Me Hear Foundation believes that a child's first years of development are critical. Being able to hear is vital to human, and Help Me Hear Foundation seeks to provide a positive lasting impression on society through its programs. Recipients of Help Me Hear Foundation's benefits receive state-of-the-art hearing devices that otherwise would cost thousands of dollars per child over the course of their lifetime. The Foundation raises money through donations for hearing aids and cochlear implants, which saves recipients and their families on average over $50,000 on related expenses. The Foundation tries to be a transparent charity, and wants to be a catalyst for allowing deaf and hearing-impaired children to develop in a typical fashion alongside their peers. Needy families can obtain information on specific services, and find out about deafness education by visiting the Help Me Hear Foundation's website. The website offers helpful information on how hearing aids work, and how hearing aids ease many of the learning and language challenges that hearing-impaired children deal with on a daily basis. \n Question: Help Me Hear Foundation was probably set up to _ . \n Options: (A) build schools for deaf children (B) research deaf children's behavior (C) protect deaf children from being ignored (D) offer real help to poor deaf children\nSolution:",
"role": "user"
},
{
"content": "D",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89940
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given an article, a question which often contains a blank and four options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer (from the given options) for the question from the given article and return one of the options from \"A\", \"B\", \"C\", and \"D\". Do not generate anything else apart from one of the following characters: \"A\", \"B\", \"C\", \"D\". There is only one correct answer for each question.\n\nArticle: Homework can put you in a bad mood , and that might actually be a good thing. Researchers from the University of Plymouth in England doubted whether mood might affect the way kids learn. To find out the answer, they did two experiments with children. The first experiment tested 30 kids. Someshapes were hidden inside a different, larger picture. The kids had to find the small shapes while sitting in a room with either cheerful or sad music playing in the background. To test their mood, the scientists asked the kids to point to one of five faces, from happy to sad. Children who listened to cheerful music tended to point to the smiley faces while the others pointed to the unhappy ones. The researchers found that sad kids took at least a second less to find the small shapes. They also found an average of three or four more shapes. In the second experiment, 61 children watched one of two scenes from a film. One scene was happy, and the other was sad. Just like in the first experiment, kids who saw the sad scene acted better compared to the others. The researchers guessed that feeling down makes people more likely to focus on a problem or difficult situation. Not all scientists agree with them, however. Other studies argued that maybe, that cheerful music in the first experiment distracted kids from finding shapes. While scientists work on finding out the answers, it still might be wise to choose when to do your tasks according to your mood. After eating a delicious ice cream, for example, write an essay. \n Question: Researchers did experiments on kids in order to find out _ . \n Options: (A) how they really feel when they are learning (B) whether mood affects their learning ability (C) what methods are easy for kids to learn (D) the relationship between sadness and happiness\nSolution: B\nWhy? It is clearly mentioned in the article that to the check effect of mood on children is the main purpose of the experiment. So, B is the correct answer.\n\nNew input: Article: When was the last time someone did something unexpectedly nice for you? Not someone you knew, but a total stranger? It's happened to me a few times, but two instances really stand out. A few years ago, I was dining out with a person who kept going on and on about himself, completely unaware of the fact that I was sitting there in misery . It wasn't his company that disappointed me. I was recovering from a bad grade in my study. I could have collapsed in tears right there at the table. When we picked up the check, the waitress said, \"Your meal was already paid for.\" My friend and I didn't have a clue how it happened. Then I remembered a man coming in out of the corner of my eye. He was dressed in mostly white, sat down at the bar, had a glass of wine, stayed for maybe ten minutes and then left. The waitress said, \"Yes, the gentleman who was in here a while ago paid for you.\" Just last year, I was running a half-marathon. With just 0.1 miles to go, I was out of gas. Runners call it \"hitting the wall\"; I thought I couldn't move another muscle. Out of nowhere, a teenager jogged up next to me and said, \"What's your name sweetie? Jennifer? Okay, Jennifer, let's go! Come on! It's just around the corner! You can do it!\". And he ran with me until I picked up my pace. I found him at the finish line to thank him for the encouragement only to learn he wasn't even supposed to be in the race that day. He was running in place of someone else. I still shake my head when I think of these momentary angels that came to me at my point of need. Do you have any experiences like this? \n Question: Why did the author say she was in misery? \n Options: (A) Because she got into trouble with her friend. (B) Because she couldn't enjoy her meal quietly. (C) Because her friend complained so much. (D) Because she was doing poorly in her study.\nSolution:",
"role": "user"
},
{
"content": "D",
"role": "assistant"
}
] |
cot
|
cot_77840
|
[
{
"content": "QUESTION: Given the sentence \"A dog is running through the snow away from the wire fence.\" is it true that \"A dog sits on a rug.\"?\n\nLet's solve it slowly: A dog can't be running outdoor and sitting on a rug at the same time.\nThe answer is no.\n[QUESTION] Test for natural language inference.\nPremise: \"A girl with a camera.\"\nHypothesis: \"Looking at the screen.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nThe girl is looking at the screen with an angry face.\nThe answer is it is not possible to tell.\nQ: Given the sentence \"A man dressed in his cultural robe.\" can we conclude that \"And sandals is waiting to cross the street.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A casually dressed man is standing by the side of the road.\nThe answer is yes.\nQUESTION: Test for natural language inference.\nPremise: \"A person is observing photos that are in frames on a wall.\"\nHypothesis: \"They are old and yellowed.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: Not all photos in frames on a wall are old and yellowed.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"Man airing up his back bicycle tire and hoping it will hold.\" is it true that \"The man is working on his bike.\"?\nAiring up a tire does not imply working on a bike.\nThe answer is it is not possible to tell.\nQ: Premise: \"A woman wearing bright colored clothing walks past a jeep cherokee that's behind a fence.\"\nHypothesis: \"A woman is sitting on a stool.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "You can't sitting down and be walking at the same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_80119
|
[
{
"content": "Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nQ: Phone rang. Jack entered the bathroom. Alexander entered the bathroom. The lime is in the green_basket. Jack moved the lime to the green_drawer. Jack entered the study. Hannah entered the study. The pumpkin is in the red_bucket. Phone rang. Jack moved the pumpkin to the blue_crate. Aiden entered the front_yard. Hannah entered the front_yard. Phone rang. The eggplant is in the green_cupboard. Aiden moved the eggplant to the red_box. Phone rang. Aiden entered the bathroom. Hannah entered the bathroom. The lime is in the green_drawer. Aiden moved the lime to the green_basket. Where will Hannah look for the lime?\nA: ",
"role": "user"
},
{
"content": "green_basket",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_10190
|
[
{
"content": "Sentence 1: now i'm not even familiar with what that where that is\n\nSentence 2: I don't know what, or even where that is.\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\nIs this second sentence entailed by the first?\n\nAnswer: yes\n\n\nQuestion:\nFront Square and Parliament Square, dating from the 18th century, are surrounded by the Chapel, Dining Hall, Examination Hall, Reading Room, and anchored by the splendid Campanile.\n\nDoes it follow that \"Parliament Square is similar in design to Front Square. \"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\nAnswer:\nit is not possible to tell\n\n\nQ: If uh one parent, can we say that \"A hundred parents!\"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nA: no\n\n\nPremise:\n\"Raphael himself appears in the lower right-hand corner.\"\nHypothesis: You can see Raphael in the low right corner.\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nyes\n\n\ninput question: He did not say another word. If this premise is true, does that tell us:\"He made a lot of noise.\"?\n\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\noutput answer: no\n\n\nQ: If 'Of course,' said Greuze., can we say that \"That's right said Greuze.\"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nA:",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
] |
cot
|
cot_92510
|
[
{
"content": "[QUESTION] If \"A man in a jacket and jeans and a woman in a green coat are reading books on a bench with a baby stroller parked next to it.\" does that mean that \"The couple is arguing over the finances as a young baby cries in hunger.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA man in a jacket and jeans and a woman in a green coat are reading books and The couple is arguing over the finances as a young baby cries in hunger.\nThe answer is no.\nQ: Given the sentence \"A group of large advertisements placed outside of a bookstore.\" can we conclude that \"The advertisments are near a bookstore.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The advertisements are near a bookstore as they are placed outside.\nThe answer is yes.\nQUESTION: Test for natural language inference.\nPremise: \"A group of muslin woman selling food at a food fair.\"\nHypothesis: \"A group of females are trying to make a sale.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: A group of Muslims are at a food fair trying to make sales.\nThe answer is yes.\n[QUESTION] Can we conclude from \"A man reaches up to work with cables above a desk.\" that \"A man is working with cables.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nJust because he reaches up to work with cables does not mean he is going to be working with cables.\nThe answer is it is not possible to tell.\nQ: Premise: \"The man is at a casino playing blackjack.\"\nHypothesis: \"A man deep ocean swimming.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: One cannot be deep ocean swimming and in a casino playing blackjack simultaneously.\nThe answer is no.\n[QUESTION] Given the sentence \"Five men all of whom are wearing white coats are standing next to lambs in an enclosed area.\" is it true that \"Five men stand next to lambs.\"?\n",
"role": "user"
},
{
"content": "Five men stand next to lams equals 5 men standing next to lambs.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_80615
|
[
{
"content": "You will be given a definition of a task first, then some input of the task.\nYou are given a dialog between 2 or more individuals. You need to generate the number of the speaker (e.g. 1 for Speaker 1) who had the most lines in the dialog. If there is a tie, output the answer '0'.\n\nSpeaker 1: So, uh, does it do anything, you know, special? \nSpeaker 2: Why yes Ross, pressing my third nipple opens the delivery entrance to the magical land of Narnia. \nSpeaker 3: You know, in some cultures having a third nipple is actually a sign of virility. You get the best huts and women dance naked around you. \nSpeaker 2: Huh? Are, uh, any of these cultures, per chance, in the tri-state area? \nSpeaker 1: You know, you are so amazing, is there anything you, you don't know? \nSpeaker 4: Ooh, Julie's so smart, Julie's so special. \nSpeaker 5: Look honey, I wanted you to hook up with Ross as much as you did. But he's with her now and you're just gonna have to get over it. \nSpeaker 4: Ohh, I'm gonna have to get over it. God, see I didn't know that's I had to do, I just have to get over it.\nOutput:",
"role": "user"
},
{
"content": "1",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84268
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s.\n\nHe grew up in Evanston, Illinois the second oldest of five children including his brothers, Fred and Gordon and sisters, Marge (Peppy) and Marilyn. His high school days were spent at New Trier High School in Winnetka, Illinois. MacKenzie studied with Bernard Leach from 1949 to 1952. _His_ simple, wheel-thrown functional pottery is heavily influenced by the oriental aesthetic of Shoji Hamada and Kanjiro Kawai. <sep>, Pronoun: His\nSolution: MacKenzie\nWhy? Based on the text, his refers to MacKenzie.\n\nNew input: In an interview with Soaplife, Price said that even though Nick has told Leanne that he still loves her, Leanne wants to be with Peter. Price added that there is always a chance with Leanne and Nick to get back together. Speaking to The Sun, Price commented: ``Nick started with Tina, then _he_moved to Kelly. <sep>, Pronoun: he\nSolution:",
"role": "user"
},
{
"content": "Nick",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_90965
|
[
{
"content": "TASK DEFINITION: In this task, you are given an input list A. You need to find all the elements of the list that are numbers in the same order as they appear in the list A.\nPROBLEM: ['P', 't', 'Y', 'a', 'p', 't', 'N', '5483', 'o', '7167']\n\nSOLUTION: 5483, 7167\n\nPROBLEM: ['4247', '4433', '5401', '7147', '5621', 'k', 'n', '5353', '6765', 'q', 'c', 'W', 'Z', 'q', 'x', '3393']\n\nSOLUTION: 4247, 4433, 5401, 7147, 5621, 5353, 6765, 3393\n\nPROBLEM: ['3993', 'K', 'V', 't', 'I', '7747', 'D', 'w', '8887', 'V', 'v', '7161', 'p', 'v', '841', '9991', '5995', 'G', 'E']\n\nSOLUTION:",
"role": "user"
},
{
"content": "3993, 7747, 8887, 7161, 841, 9991, 5995\n\n",
"role": "assistant"
}
] |
cot
|
cot_65066
|
[
{
"content": "[QUESTION] Given the sentence \"A woman walks along a street as she looks to a window display of a mannequin in a red dress.\" is it true that \"The woman is considering buying the dress.\"?\nLooking at a window display with a dress does not imply she is considering buying it.\nThe answer is it is not possible to tell.\n\n[QUESTION] Given the sentence \"Three men are standing on a rather large extended platform to a cherry picker.\" is it true that \"And they are posing for a group work picture.\"?\nThree men are falling to their death off of a cherry picker.\nThe answer is no.\n\n[QUESTION] Test for natural language inference.\nPremise: \"A young girl in colorful leggings is carrying a brightly colored flag in a parade.\"\nHypothesis: \"A young lady has colorful clothes in the parade.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nLeggings are a type of clothes and girl is another way to say lady.\nThe answer is yes.\n\n[QUESTION] Premise: \"Two girls swing on a tire swing.\"\nHypothesis: \"There are two boys on a tire swing.\"\nDo we know that the hypothesis entailed by the premise?\n",
"role": "user"
},
{
"content": "The people on the swing must be either two girls or two boys.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89595
|
[
{
"content": "In this task, you're given four sentences of a story written in natural language. The given story is not complete and your job is to complete the story by selecting one of the end sentence choices from (A) and (B), such that the story does not sound complete and coherent, i.e., select an incorrect end sentence.\n--------\nQuestion: Sentence1: Tine wanted to make the track team. Sentence2: She hoped she was fast enough. Sentence3: For a month before tryouts, she ran on her own. Sentence4: She rose early every morning to run for miles. \n (A) Tine made the team with the best time of anyone. (B) Tine sat on the couch and ate bonbons instead of trying out.\n\nAnswer: B\n\n\nQuestion: Sentence1: Tom bought a new plant. Sentence2: He kept it by his bed. Sentence3: The plant stopped growing. Sentence4: His mother said it needed sunlight. \n (A) So Tom moved the plant to a window. (B) Tom closed his windows to block out as much sunlight as possible.\n\nAnswer: B\n\n\nQuestion: Sentence1: Oliva wanted to go shopping. Sentence2: She decided to go to the mall. Sentence3: She found a great sale on shoes. Sentence4: She bought three pairs. \n (A) Olivia decided to never go shopping again. (B) Oliva had a great day shopping.\n\nAnswer:",
"role": "user"
},
{
"content": "A\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_66748
|
[
{
"content": "Q: Premise: \"A woman wearing rolled up jeans passing bus a pass whose ad appears to be checking her out.\"\nBased on this premise, can we conclude that the hypothesis \"A woman is being passing an ad on a bus.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A woman is being passing is rephrasing passing bus a pass.\nThe answer is yes.\nQUESTION: Given the sentence \"Two mountain climbers stand on the ridge of a tall.\" can we conclude that \"Snowy mountain.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Two people are sitting at the top of a grassy hill.\nThe answer is no.\n[QUESTION] Given the sentence \"A man with black glasses making balloon creations for children.\" is it true that \"A clown entertains children with juggling.\"?\nClowns don't normally wear black glasses. Making balloon creatures is different from juggling.\nThe answer is no.\nQ: Can we conclude from \"People are at their job creating clothing.\" that \"People are fishing for marlin.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Creating clothing and fishing cannot be done at the same time.\nThe answer is no.\nQUESTION: Given the sentence \"Old man carries a bag down the street.\" is it true that \"The is walking with a heavy bag he just found.\"?\n\nLet's solve it slowly: Carries a bag does not imply it is heavy or that he just found it.\nThe answer is it is not possible to tell.\nQUESTION: Premise: \"A man in jeans reclines while another watches.\"\nHypothesis: \"A man is wearing a t shirt.\"\nDo we know that the hypothesis entailed by the premise?\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "We don't know if he is wearing a t shirt or even pants. He may be balls out.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
cot
|
cot_87800
|
[
{
"content": "QUESTION: Given the sentence \"Girl wearing black shirt and purple shorts swings on rope on boat.\" can we conclude that \"A girl is sitting at her desk in school.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: You cannot be at school and on a boat at the same time.\nThe answer is no.\n[QUESTION] Test for natural language inference.\nPremise: \"A large man is stopped at an intersection on a scooter.\"\nHypothesis: \"A small man was stopped at an intersection by a scooter.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nMajor contradiction in mention of a large man and a small man in the two cases.\nThe answer is no.\nQ: Premise: \"A man in a blue hat has his foot on the front bumper of a van.\"\nBased on this premise, can we conclude that the hypothesis \"A man is touching the van.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: It is possible to have foot on the front bumper of a van only by touching the van.\nThe answer is yes.\nQUESTION: Test for natural language inference.\nPremise: \"A boy in an over-sized dress shirt sits outside a shop next to a pile of new sandals.\"\nHypothesis: \"A boy is shirtless.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: If the boy is in an over-sized dress shirt then he cannot be shirtless.\nThe answer is no.\n[QUESTION] Premise: \"A group of people in front of a house.\"\nHypothesis: \"The group of people are having a meeting infront the house.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nPeople do not have to be having a meeting because they are in front of the house.\nThe answer is it is not possible to tell.\nQ: Test for natural language inference.\nPremise: \"Another man in a gray sweatshirt also rides a horse.\"\nHypothesis: \"A man rides a horse.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA:",
"role": "user"
},
{
"content": "A man rides a horse and another man rides a horse also.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_74040
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nthe average of the home team score record of all rows is 12.07 .\n",
"role": "user"
},
{
"content": "round_eq { avg { all_rows ; home team score } ; 12.07 }",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_90084
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nInput: Consider Input: select the rows whose no of series record is equal to 3 . select the row whose episodes record of these rows is minimum . the actor record of this row is ellen thomas .\n\nOutput: eq { hop { argmin { filter_eq { all_rows ; no of series ; 3 } ; episodes } ; actor } ; ellen thomas }\n\n\nInput: Consider Input: the average of the secondary ( 14 - 17 years ) record of all rows is 70.95 .\n\nOutput: round_eq { avg { all_rows ; secondary ( 14 - 17 years ) } ; 70.95 }\n\n\nInput: Consider Input: the 1st minimum date record of all rows is 03 oct . the time record of the row with 1st minimum date record is 12:00 .\n\n",
"role": "user"
},
{
"content": "Output: and { eq { nth_min { all_rows ; date ; 1 } ; 03 oct } ; eq { hop { nth_argmin { all_rows ; date ; 1 } ; time } ; 12:00 } }\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82430
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nLet me give you an example: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.\nThe answer to this example can be: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 }\nHere is why: Here, the generated command using logical operators correctly selects third maximum from given table rows which is mentioned in natural language interpretation.\n\nOK. solve this:\nselect the rows whose position record fuzzily matches to centre - left . the number of such rows is 2 .\nAnswer:",
"role": "user"
},
{
"content": "eq { count { filter_eq { all_rows ; position ; centre - left } } ; 2 }",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_80167
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nselect the row whose year record of all rows is 3rd minimum . the title of movie record of this row is a flight to yesterday 《 飛往昨天的ci006 》 .\n",
"role": "user"
},
{
"content": "eq { hop { nth_argmin { all_rows ; year ; 3 } ; title of movie } ; a flight to yesterday 《 飛往昨天的ci006 》 }",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86817
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nExample Input: for the manner of departure records of all rows , most of them fuzzily match to contract ended .\nExample Output: most_eq { all_rows ; manner of departure ; contract ended }\n\nExample Input: the 2nd maximum weeks record of all rows is 16 weeks .\nExample Output: eq { nth_max { all_rows ; weeks ; 2 } ; 16 weeks }\n\nExample Input: select the rows whose performer record fuzzily matches to kaliopi . take the rank record of this row . select the rows whose performer record fuzzily matches to marjan necak . take the rank record of this row . the first record is less than the second record .\nExample Output:",
"role": "user"
},
{
"content": "less { hop { filter_eq { all_rows ; performer ; kaliopi } ; rank } ; hop { filter_eq { all_rows ; performer ; marjan necak } ; rank } }\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91258
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n--------\nQuestion: select the rows whose name record fuzzily matches to arrowtown school . take the decile record of this row . select the rows whose name record fuzzily matches to glenorchy school . take the decile record of this row . the first record is greater than the second record .\n\nAnswer: greater { hop { filter_eq { all_rows ; name ; arrowtown school } ; decile } ; hop { filter_eq { all_rows ; name ; glenorchy school } ; decile } }\n\n\nQuestion: select the rows whose home team record fuzzily matches to fitzroy . take the home team score record of this row . select the rows whose home team record fuzzily matches to north melbourne . take the home team score record of this row . the first record is greater than the second record .\n\nAnswer: greater { hop { filter_eq { all_rows ; home team ; fitzroy } ; home team score } ; hop { filter_eq { all_rows ; home team ; north melbourne } ; home team score } }\n\n\nQuestion: select the row whose age record of all rows is maximum . the name record of this row is donte gamble .\n\nAnswer:",
"role": "user"
},
{
"content": "eq { hop { argmax { all_rows ; age } ; name } ; donte gamble }\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_76014
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nselect the row whose race record of all rows is 2nd minimum . the season record of this row is 2008 .\n",
"role": "user"
},
{
"content": "eq { hop { nth_argmin { all_rows ; race ; 2 } ; season } ; 2008 }",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_85660
|
[
{
"content": "In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\n[EX Q]: select the rows whose total dismissals record is less than 10 . the sum of the total dismissals record of these rows is 8 .\n[EX A]: round_eq { sum { filter_less { all_rows ; total dismissals ; 10 } ; total dismissals } ; 8 }\n\n[EX Q]: the maximum population ( 2010 census ) record of all rows is 241528 . the district record of the row with superlative population ( 2010 census ) record is sampaloc .\n[EX A]: and { eq { max { all_rows ; population ( 2010 census ) } ; 241528 } ; eq { hop { argmax { all_rows ; population ( 2010 census ) } ; district } ; sampaloc } }\n\n[EX Q]: select the row whose launch date record of all rows is 2nd maximum . the name record of this row is corot .\n[EX A]:",
"role": "user"
},
{
"content": "eq { hop { nth_argmax { all_rows ; launch date ; 2 } ; name } ; corot }\n\n",
"role": "assistant"
}
] |
cot
|
cot_53956
|
[
{
"content": "[QUESTION] Given the sentence \"A black man is pointing at a sign.\" is it true that \"A man has his arm up toward the sign.\"?\nIf the man is pointing at a sign then his arm is up.\nThe answer is yes.\nQ: Given the sentence \"Women in pink dress with white polka dots standing on stone base shoo-shes those in view.\" is it true that \"The woman quiets the crowd.\"?\nA: Just because women in pink dress with white polka dots standing on stone doesn't mean she quiets the crowd.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"Two gay guys having fun with a weiner.\" can we conclude that \"The men are boyfriends.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Gay guys do not have to be boyfriends to be having fun.\nThe answer is it is not possible to tell.\n[QUESTION] Premise: \"A woman in a light blue shirt.\"\nHypothesis: \"Resting against a rock.\"\nDo we know that the hypothesis entailed by the premise?\nThe woman is in a red shirt resting on the ground.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"Three children are posing on a playground slide.\"\nHypothesis: \"Three children about to tumble down a slide.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Not all children near slides are about to tumble down them.\nThe answer is it is not possible to tell.\n[QUESTION] Premise: \"A group a people walk around the corner near a brick building.\"\nHypothesis: \"A group of people are heading into a building.\"\nDo we know that the hypothesis entailed by the premise?\n",
"role": "user"
},
{
"content": "Just because walk around corner does not mean heading into a building.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86740
|
[
{
"content": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\nOne example is below.\nQ: Sentence 1: The cashier was counting the dollar bills at her desk. \n Sentence 3: Everyone panicked and started to scream. \n Sentence 4: The men threatened the people to remain quiet. \n Sentence 5: The cashier handed them the cash so they would go away. \n Option 1: Two men rushed into the store and held their guns up. \n Option 2: Two dogs rushed into the store.\nA: Option 1\nRationale: Option 1 forms a consistent story with the given four sentences. In constrast, Option 2 is incorrect as the entty 'two dogs' is not consistent with 'men' mentioned in Sentence 4.\nQ: Sentence 1: Jason was playing on the floor building a card house. \n Sentence 3: Jason was furious \n Sentence 4: He jumped up and shoved his brother \n Sentence 5: His mother saw and punished Jason \n Option 1: His brother helped, and they took a picture. \n Option 2: His younger brother ran in the room knocking down the house.\nA:",
"role": "user"
},
{
"content": "Option 2",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89608
|
[
{
"content": "instruction:\nIn this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nquestion:\n15, 18, ['Z', 'K', '8837', '8023', 'H', '4565', 'u', 'Y', 'o', 'x', 'I', 'u', '941', '5425', 'l', 'L', 't', 'P', 'r', 'G', '7207', '7491', '5969', '6967', '1029']\nanswer:\nP, t, L, l\n\n\nquestion:\n3, 11, ['3395', 'x', 'B', '4803', 'q', '8513', '4391', '3193', 'R', 'i', 'q', '2993']\nanswer:\nq, i, R, 3193, 4391, 8513, q, 4803, B\n\n\nquestion:\n2, 6, ['m', 'e', '501', 'I', 'K', 'G', 'V', '3533', '4903', 't', 'f', 'U', '2981', 'P', 'w', 'h']\nanswer:\n",
"role": "user"
},
{
"content": "G, K, I, 501, e\n\n\n",
"role": "assistant"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.