Search is not available for this dataset
conversations
listlengths 2
2
|
---|
[
{
"from": "human",
"value": "In this task, you will be presented with a question, a word, and a POS tag. You have to determine whether the part-of-speech tag of the given word in the question is equal to the given POS tag or not. Give your answer with True or False. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\n\nHow many times has the author of King Rat won the Arthur C. Clarke Award ? \n, Word: times \n, POS tag: NNS"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your 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. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.\n\nInput: Consider Input: Context Word: exercises. \nQuestion: PersonX did a lot of exercises but PersonY did not because _ had very good fitness levels. \nAnswer: PersonX\n\nOutput: PersonX did a lot of exercises but PersonY did not because _ had very bad fitness levels.\n\n\nInput: Consider Input: Context Word: clean. \nQuestion: PersonX's home isn't nearly as clean as PersonY's because _ has always been a messy person. \nAnswer: PersonX\n\nOutput: PersonX's home isn't nearly as clean as PersonY's because _ has always been a tidy person.\n\n\nInput: Consider Input: Context Word: voodoo. \nQuestion: PersonX doesn't believe in voodoo, but PersonY does, so _ is more likely to be Christian. \nAnswer: PersonX\n\n"
},
{
"from": "gpt",
"value": "Output: PersonX doesn't believe in voodoo, but PersonY does, so _ is more likely to be a pagan.\n\n\n"
}
] |
[
{
"from": "human",
"value": "Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.\n\n[Q]: How much does meth cost you denver ?\n[A]: Bad\n\n\n[Q]: What is the size of standard queen mattress ?\n[A]: Bad\n\n\n[Q]: Comparative analyzes of demand and supply ?\n[A]:"
},
{
"from": "gpt",
"value": "Bad\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\n\nExample input: Article: There are a lot of public libraries in Britain. These libraries have more than one hundred and fifteen million books, not including those libraries of public schools. Public libraries not only lend books, music records but also help children, patients in hospitals and others to get special play readings, film shows and so on. The first public libraries were founded in about the year 1850. Today's public libraries usually have a reading-room, a lending room and a reference room. The greatest and most famous library in Britain is that of the British Library in London. It was founded in 1973 and has over 10, 000, 000 books. It has nearly every magazine, newspaper and book published in Britain and other parts across the world. \n Answer: 10,000,000 or less.\nExample output: How many books are there in the British Library?\nExample explanation: In the Article, 10,000,000 is mentioned for the number of books available in the British Library, so this is a good question.\nQ: Article: The origination of the \"gap year\" concept came in the decade following the Second World War when youth travel and cultural exchange was discussed among governments as a useful tool to create more of a global understanding to prevent future global wars. However, the first gap years actually started in the UK in the 1960s when the Baby-Boomer generation in the midst of the Swinging Sixties headed off to India on the infamous Hippie Trails ,inventing the independent travel market. Australian Graham \"Screw\" Turner, based in London in 1973, loaded a double-decker bus with the first paying customers and drove them to Kathmandu. They arrived three weeks late. Top Deck Travel, the company he founded, still exists today. In 1979 another Australian, Dick Porter, founded STA Travel to bring in the final piece of the puzzle. It was a high street travel agent for students and youth (those under 26) with which he was able to develop global youth travel as he opened student travel agencies around the world. In the UK in the 1980s the Baby-Boomers were accustomed to family life with their young children and so traveling less, and the next generation were influenced by the addiction to money, careers and wealth. The housing market crash meant fewer funds available for parents to fund youth travel. But steady UK and global growth continued as STA Travel opened up branches around the world. A combination of the Baby-Boomer's children reaching 18 (whose parents encouraged world travel as they did in their youth), the UK coming out of decline and new, exciting, color1ful media channels to bring gap year products to market resulted in an explosion of activity in the UK in the 1990s as gap year travel and gap year volunteering took off pre-, during, and post-university. Demand grew, prices for air travel fell, and the roots of it becoming a tradition of growth were set. The modern gap year pioneers came in the form of Tom Griffiths and Peter Pedrick who brought the gap year market onto the web in 1988 with the launch of www.gapyear.com. The two pioneers have invented products, offerings, phrases, and concepts that form the frame of the global gap year industry seen today. Known as the gap year guru. Tom Griffiths is recognized as a global authority on gap years and acts as a media spokesperson around the world. \n Answer: Because the governments wanted to guard the world against future global wars.\nA:"
},
{
"from": "gpt",
"value": "Why was the \"gap year\" concept was originated in the decade after the World War II ?"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a dialogue between a customer and a flight booking agent with a gap in the conversation. Your job is to find the answer of the previous dialogue. Avoid using irrelevant extra information while creating the answer. The answer should be relevant to the question before the blank. If you fill the blank with a question, it should have an answer from the agent in the given dialogue. Fill the gap marked with underline.\n\ncustomer: Hello, I am Sharon Green. \n agent: Hello, how may I help you? \n customer: I would like to celebrate Steampunk festivals with my family at New York, NY - LGA. Will you help me to book a connecting flight? \n agent: Sure, please share your journey dates? \n __ \n agent: May I know your origin airport code? \n customer: Sure, Phoenix, PHX is my origin airport code. \n agent: Do you need any price limit? \n customer: Yes, I can spend up to 500. \n agent: Sorry, no flights found on your given dates. \n customer: Ok, no worries at all. \n agent: Thank you for choosing us. \n customer: Thank you.\nOutput:"
},
{
"from": "gpt",
"value": "customer: Ok, my journey dates are 10/24 and 10/26."
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In 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: like many other posts here, this happened (6)years ago. \nmy school (in germany) had this exchange every year for the 9th graders with a school in southern france so we could learn french and they could learn german. first me and my class went to france for two weeks and stayed with a student of that french school and after two months they would come and the student we stayed with would stay with us for two weeks. we will call the guy i stayed with tom.\nduring the two weeks in france me and tom became pretty good friends and had a really good time. i had expected it to be awkward but his family was really nice and we got along well from the first day. since his mother could also speak english(quite rare in france) communicating wasnt a big issue either. \nnote: in france(at least where i went) people of the opposite sex greet each other with a kiss on each cheek(even school kids). \nthe two months pass and tom arrives in germany and i had forgotten all about the cheek kissing thing. we arrive at my house and my dad is waiting for us with my little brother and little sister(only 2.5 years younger and looks like my age and very shy). tom shakes my dads hand says hi to my little brother and goes over to my sis and starts leaning in slowly to kiss her on the cheek. my sister(not knowing what he is trying to do) leans backwards. he keeps leaning in. i'm like \"wait. wtf is going on?\". my teenage mind was way too slow to process what was going on and prevent the awkwardness. when i finally get it i tell him that we dont do that shit here and he quickly backs up and apologised countless times and that he didnt know. he and my sister went red like tomatoes and you could cut the awkwardness with a knife. my brother and parents thought it was hilarious and laughed about it for weeks.\ntom and my sister pretty much avoided each other for the two weeks.\n"
},
{
"from": "gpt",
"value": "TIFU by not telling the french exchange student i was resposible for how we greet people in Germany"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Decide the language of that sentence. The language can be English, French, German, Italian, or Spanish.\nSee one example below:\nProblem: Text: 'try and ehm go as close to ravine as possible but up towards the carved stones'.\nSolution: English\nExplanation: This is an English sentence.\n\nProblem: Text: 'you're heading from the indian country to the gold mine but trying to avoid the gold rock so come down to the bottom of'\nSolution:"
},
{
"from": "gpt",
"value": "English"
}
] |
[
{
"from": "human",
"value": "Definition: In this task your given two statements in Indonesian. You must judge whether the second sentence is the cause or effect of the first one. Label the instances as \"cause\" or \"effect\" based on your judgment. The sentences are separated by a newline character.\nInput: Perempuan itu injak es.\nIa terselip.\nOutput:"
},
{
"from": "gpt",
"value": "effect"
}
] |
[
{
"from": "human",
"value": "In this task, given a sentence in the Malay language, and your task is to convert it into the English language.\n\nQ: Fosse mengatakan bahawa OSCE, Jambatan Negeri A.S. dan Pertubuhan Bangsa-bangsa Bersatu telah mengkritik Perancis \"mencabuli hak asasi manusia.\"\n\nA: Fosse said that the OSCE, the U.S. State Department and the UN had criticised French \"violations of human rights\".\n****\nQ: Banyak pasar raya di Kesatuan Eropah telah secara sukarela menerima pakai kaedah untuk mengurangkan penggunaan beg plastik, yang sering juga terdiri daripada mengenakan bayaran bagi beg (contohnya Jerman) atau memberi ganjaran mata kesetiaan pelanggan untuk mengembalikan beg pengangkut terpakai.\n\nA: Many supermarkets in the European Union have voluntarily adopted methods to reduce usage of plastic bags, which often also consist of charging for bags (e.g. Germany) or rewarding customer loyalty points for returning used carrier bags.\n****\nQ: Penduduk bersedia menghadapi nor'easters terburuk dalam tempoh beberapa ketika.\n\nA:"
},
{
"from": "gpt",
"value": "Residents prepared for what would be one of the worst nor'easters in quite some time.\n****\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.\nOne example is below.\nQ: [[7, -3, -3, 11], [-6, -6, -5, 2], [-8, 4, -3]]\nA: [0, 72, -32]\nRationale: The first inner list has no even integers, so the first number in the output is 0. The second list has -6, -6, 2 for even integers so the second output is 72. The third list has -8, 4 as even numbers so the third output is -32. This is a good example.\nQ: [[40, 40], [27, -23], [5, -46], [29, 32, 10], [30, 40, 0, -23]]\nA:"
},
{
"from": "gpt",
"value": "[1600, 0, -46, 320, 0]"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Given a sentence, generate a most unlikely next statement. The next statement should not be logically relevant to the given context\n\nThe scene is of a neighborhood surrounded by tall trees and a pile of dead leaves next to a leaf catcher. A man holding a rattle\n"
},
{
"from": "gpt",
"value": "brushes and continues on it."
}
] |
[
{
"from": "human",
"value": "Given a sentence in Tagalog language, translate the sentence to English language keeping the meaning of the original sentence intact.\n--------\nQuestion: Tagalog sentence: Sa anumang pangyayari, siya namatay sa utang, 'ang mga patakaran sa loob ng' ng King's bench sa bilangguan, kung saan ay nakatayo sa Southwark; ang quoted phrase sinadya na ang mga bilanggo ay binili ng karapatan na manirahan sa loob ng isang maikling distansya ng bilangguan. Taong gustong sabong ng lumipat sa Southwark ay marahil ng isang enforced isa, dahil sa kanyang pagpapasok sa bilangguan para sa utang.\n\nAnswer: In any event, he died in debt, 'within the rules' of the King's Bench Prison, which was situated in Southwark; the quoted phrase meant that the prisoner had purchased the right to live within a short distance of the prison. Cocker's move to Southwark was probably an enforced one, consequent on his committal for debt.\n\n\nQuestion: Tagalog sentence: Makinig Ang kanilang Telepono Pag-uusap\n\nAnswer: Listen Their Phone Conversation\n\n\nQuestion: Tagalog sentence: Maaari tayong tumugon sa mga sumusunod na pamamaraan: 1) Nais mo bang panagutan ang kasalanan ng mga tao na nagkasala mahigit 900 taon na ang nakararaan? 2) Nais mo bang panagutan ang mga kasalanan ng lahat ng nagsasabi na sila ay Kristiyano nunit hindi totoong Kristiyano? Ang paninisi sa buong sangka -Kristiyanuhan para sa mga krusada ay katulad din ng paninisi sa lahat ng mga Muslim para sa mga gawain ng terorismo ng Islam. Bumalik sa Tagalog Home Page Ano ang mga krusadang Kristiyano? Maghanap para sa:\n\nAnswer:"
},
{
"from": "gpt",
"value": "We can respond in the following ways: 1) Do you want to be held accountable for the actions of people who lived 900+ years ago? 2) Do you want to be held accountable for the actions of everyone who claims to represent your faith? Trying to blame all of Christianity for the crusades is analogous to blaming all Muslims for Islamic terrorism.\n\n\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task you are given a statement and an explanation giving you further knowledge about an entity in the statement. You must judge whether the statement is true or false based on the explanation. Label an instance as \"True\" if the explanation confirms the statement or doesn't disprove it. Label an instance as \"False\" if the explanation disproves the statement. The statement and explanation are separated by a newline character.\nTim Duncan played basketball for a professional team in Texas.\nTim Duncan was a member of the NBA team The Spurs, based in San Antonio, Texas.\nA:"
},
{
"from": "gpt",
"value": "True"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\n\nOne sitting man and the other is standing while holding a conversation\n"
},
{
"from": "gpt",
"value": "(2, 3)"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you are given two simple actions (associated with \"A\", \"B\"). You must identify which action is considered less ethical. Do not generate anything else apart from one of the following characters: 'A', 'B'.\nPROBLEM: (A) not wanting my future kid to go to public school\n(B) not wanting to go out with my sister\n\nSOLUTION: A\n\nPROBLEM: (A) not being my mother's friend\n(B) being mad at my parents for putting my sister over me\n\nSOLUTION: A\n\nPROBLEM: (A) deadbolting our door\n(B) not wanting to pay $18.50 to my boyfriend for ingredients for a dish I'll serve at my Mother's memorial\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "B\n\n"
}
] |
[
{
"from": "human",
"value": "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\n[Q]: Title: Bruised. Sentence 1: Anna was playing football in gym at school. Sentence 2: She tossed the ball to her teammate. Sentence 3: But he didn't catch it - it caught him! Sentence 4: It hit him on the cheek. Choices: a. Anna was proud of her ingenuity! b. He ended up with a big purple bruise!\n[A]: a\n\n\n[Q]: Title: Chubby. Sentence 1: Anna had always liked her curvy figure. Sentence 2: Then one day she overheard some boys joking about her. Sentence 3: They made fun of her chubby face and features. Sentence 4: For a moment Anna was devastated - but then she recovered. Choices: a. She was relieved when she pulled up to her dormitory. b. She resolved not to let anyone else affect her self-esteem!\n[A]: a\n\n\n[Q]: Title: The Board Game. Sentence 1: The family gathered around the table. Sentence 2: They were going to play a new board game. Sentence 3: They tried to figure out the rules, but it was so confusing! Sentence 4: They finally gave up. Choices: a. Anna's picnic party idea was a success. b. They played Monopoly instead.\n[A]:"
},
{
"from": "gpt",
"value": "a\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you have to generate the named entities (NER) given its ingredients of the recipe. Named entities are the names of the items without their quantity.\nOne example is below.\nQ: 1 3/4 cups all purpose flour, 1/4 cup finely ground blanched almonds, 1 teaspoon grated lemon zest, 1/2 cup confectioners sugar, 2 sticks unsalted butter, almost melted, 4 eggs, lightly beaten, 2 cups granulated sugar, 1/4 cup flour, 1/2 teaspoon baking powder, 2 teaspoons grated lemon zest, 1/3 cup fresh lemon juice, Candied violets for garnish, optional\nA: flour, ground blanched almonds, lemon zest, confectioners sugar, butter, eggs, sugar, flour, baking powder, lemon zest, lemon juice, Candied violets\nRationale: Given the required ingredients, the ner of the recipe is generated. As the ingredients contain the quantities, if we just remove quantities from ingredients, we get the ner.\nQ: 7/8 cup watermelon liquefied, 32 3/4 feet kirsch, ice, cherries for garnish\nA:"
},
{
"from": "gpt",
"value": "watermelon liquefied, feet kirsch, cherries"
}
] |
[
{
"from": "human",
"value": "Instructions: You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For consistency, answers should be in all lower cased letters.\nInput: Category: FASHION \nClue: This puckered & striped cotton suit for men can now be found in a variety of styles & colors\nOutput:"
},
{
"from": "gpt",
"value": "seersucker"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, a passage will be given and the goal is to generate a question about temporal relations based on that passage. A temporal relation describes the relation between two things with respect to time e.g., something happens/starts/terminates/... immediately/shortly/usually/... before/after/during/... something else.\n Your question should include an event, or ask about an event, and should not be a yes/no question.\nQ: Passage: He also said the bilateral economic and trade cooperation had seen rapid development and that his government is implementing big projects funded by Chinese loans. Enkhbayar said that during his visit, the two sides would discuss how to expand cooperation in economy, trade and other fields.\nA:"
},
{
"from": "gpt",
"value": "What event has already finished?"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\nExample: Premise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student\nExample solution: strengthener\nExample explanation: If PersonX was a good student, it is more likely that PersonX would do good activities.\n\nProblem: Premise: PersonX takes PersonX's exam\nHypothesis: Before, PersonX needed to be all the stationery required\nUpdate: PersonX was taking the SAT.\n"
},
{
"from": "gpt",
"value": "Solution: weakener"
}
] |
[
{
"from": "human",
"value": "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 the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\n\nMiddle: Helen planned to drive to Canada but it started snowing heavily. Ending: Helen stayed home instead and planned to go another day.\nSolution: Helen lived in America.\nWhy? Mention of the destination country name and driving implies that Helen is from a nearby foreign country.\n\nNew input: Middle: Zeke moved to Canada and made new friends. Ending: Zeke lived out his life very happy.\nSolution:"
},
{
"from": "gpt",
"value": "Zeke was tired of living in America."
}
] |
[
{
"from": "human",
"value": "Teacher: You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nhe look into your eye that same look just take your breathe away you feel at that moment that he be definitely the one for you but just when you realize that just as fast a he take your breathe away he take your heart and break it into tiny little piece and watch it burn\nSolution: high\nReason: The poem is long and linguistically well structured, and the prediction is correct.\n\nNow, solve this instance: this life be the sparkle ocean i be aware of my vulnerablity destiny be my lead yet i choose each path though sometimes ocean may be calm gently ripple sometimes there be tsunami wash away the weak i 've hear i be glue to the wave move with them a the crash & amp settle i be not afraid of time hard to hold on i do not fear for i be a snake bend & amp blend with my destiny but i choose my reaction forever change my world i promise there shall be struggle i accept this gratefully i be the snake move with the water that may carry or crash it be journey one i will happily survive\nStudent:"
},
{
"from": "gpt",
"value": "high"
}
] |
[
{
"from": "human",
"value": "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 seamlessly connects with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes more sense.\n\n[EX Q]: Title: New Traditions. Sentence 1: Finn was celebrating the holidays with his new girlfriend. Sentence 2: They were both attached to family traditions. Sentence 3: Neither could agree about how to do anything. Sentence 4: Instead they decided to create their own traditions. Choices: a. And so he became the worst Twitch streamer there ever was. b. They blended all of their favorite and enjoyed their own holiday.\n[EX A]: b\n\n[EX Q]: Title: Fish. Sentence 1: I went on a trip with my class in college. Sentence 2: We took some canoes. Sentence 3: We saw fish a foot long. Sentence 4: They were swimming around our feet. Choices: a. We were unable to grab one. b. Due to her success, Diane was re-elected as union president.\n[EX A]: a\n\n[EX Q]: Title: Smelly Fridge. Sentence 1: John was at home. Sentence 2: He was thirsty. Sentence 3: He opened the fridge to see what he had to drink. Sentence 4: When the fridge was opened a very bad smell came out. Choices: a. John quickly cleaned the fridge. b. Old Red was a fun animal to play with.\n[EX A]:"
},
{
"from": "gpt",
"value": "a\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you are given two simple actions (associated with \"A\", \"B\"). You must identify which action is considered less ethical. Do not generate anything else apart from one of the following characters: 'A', 'B'.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n(A) trying to be a decent parent\n(B) remaining Friendly with my racist coworker\nSolution: B\nReason: action (B) is not ethical.\n\nNow, solve this instance: (A) responding late in the group chat\n(B) wanting to split up with my so because my physical attraction to her has diminished, and being honest if she asks why? this woman is otherwise perfect (career, stable, caring, etc.) I'm a solid 8/10 overall, I don't think my standards are too high, I know looks fade, etc\nStudent:"
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "In this task, you will be presented with the directions of a recipe separated by \",\" and have to fill in the \"___\" which is a step that is missing from the recipe.\nOne example: Preheat oven to 325F and grease and flour a 10\" tube pan.,Soak the nutmeg in the whiskey for ten minutes.,______,Cream butter and sugar together until fluffy.,Add eggs, one at a time until well incorporated.,Fold in remaining 1 1/4 cups flour, cream of tartar, baking soda, salt, soaked nutmeg and pecan/raisin mixture until well combined.,Spoon into prepared pan.,Bake for 1 hour and 15 minutes or until cake pulls away slightly from the edge of the pan.,Let stand in the pan for 30 minutes, then turn out onto cooling rack for complete cooling.,Store in an airtight container.\nSolution is here: Stir together pecans, raisins, and 1/4 cup flour; set aside.\nExplanation: This is a good example, as we see the missing step is generated correctly from the available directions.\n\nNow, solve this: Place mushrooms in a small bowl with 3/4 c. of water.,Microwave on high till water boils; remove and let mushrooms cold to room temperature.,Heat oil in a large dutch oven over medium heat.,Brown brisket on one side.,Turn and add in onions; continue browning.,When onions are brown, add in garlic; cook 1 minute more.,Remove mushrooms from soaking liquid (reserve liquid).,Rinse mushrooms and chop.,Strain soaking liquid through a coffee filter to remove grit.,Pour in beef broth and mushroom liquid.,Add in bay leaf, salt, and pepper.,Cover; reduce heat to low and cook 2 to 2 1/2 hrs, till brisket is tender.,______,Increase heat to high and cook till juices thicken slightly.,Remove bay leaf.,Cut brisket against the grain into thin slices.,This recipe yields 6 servings.,Description: \"A small handful of dry mushrooms add in lots of flavor to this traditional dish.,If you are a real mushroom fan, add in a c. of sliced sauteed mushrooms just before serving.\"\nSolution:"
},
{
"from": "gpt",
"value": "Transfer brisket to a cutting board."
}
] |
[
{
"from": "human",
"value": "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\n[EX Q]: Personality: I'm a humble baker.\nI look forward to retiring.\nI tried to make it as an actor when I was younger.\nMy wife always puts a smile on my face.\nChat history: -Hello, do you have any siblings?\n -No I am the only one, do you?\n -Yes, four of them, but I am the oldest.\n -That's pretty cool, what you do for living.\n -I'll probably go into teaching, as my father teaches middle school. You?\n -Nice, I'm a baker, I'm ready to retire, how old are you.\n -Well, my youngest sibling is in first grade, if that gives you an idea.\n[EX A]: O wow, haha you are very young.\n\n[EX Q]: Personality: I enjoy reading.\nI m going back to school.\nI m a vegan.\nI love animals.\nI love country.\nChat history: -Hello what do you like to do?\n -Hello, Tracy here. Beef is my fave.\n[EX A]: Ew I'm Vegan but I also like to read.\n\n[EX Q]: Personality: I love music of the 1980s, especially the pretenders.\nMy favorite food is spicy tex mex.\nI've a puppy named tiki.\nI studied early childhood education in college.\nChat history: -How are you doing today?\n -Good, thanks. Been mainly playing with my cute little puppy haha.\n -Just got back from some training for a marathon myself.\n -Oh you enjoy going for a run?\n -A new puppy? Awesome what kind? Yeah no people.\n -A pug called tiki! Haha, I'm not a people person either. Prefer dogs.\n -Fun. Yeah when I hang with people just say not the right kind of things.\n[EX A]:"
},
{
"from": "gpt",
"value": "I feel you! Dogs love you no matter what you say haha.\n\n"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here.\nInput: Dopinder: I presume a crisp high _ five _ ?\nDeadpool: For you ? 10 .\nDeadpool: Okay\nDeadpool: , guys , let 's get out there and make a difference .\nDeadpool: You know what do to .\nDopinder: Knock 'em dead , Pool Boy !\nOutput:"
},
{
"from": "gpt",
"value": "OTHER"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to find the correct answer (and return the string of the correct option, not option1/2) for the given question from the given options and based on the given passage. Answer of the question can be found directly from the passage.\n\nPassage: Omelettes make a great breakfast , and I enjoy making them because they are very easy to cook . First , I get the eggs out and begin cracking them on the side of the bowl and dumping them into the bowl . I normally use two eggs whites and one whole egg to cut the calories . I add some salt and pepper to the mix for flavor . I pour the mixture into the hot frying pan . I make sure that I add some vegetable oil to the pan before I add the eggs though because I do n't want them to stick . As this occurs , I add some cheese or vegetable to the center of the egg mixture . Really , almost any type of cheese or vegetable makes a good omelette . I then flip one side of the omelette over on to itself to seal in the contents in the middle . It is then ready to serve ! Question: How many times is the omelette flipped? Option1: three times Option2: once\nSolution: once\nWhy? As mentioned in the passage that I then flip one side of the omelette; it is clear that omelette is flipped one time only.\n\nNew input: Passage: The bell rang , But I was not especially excited to get out of school today . For tomorrow were exams . And I had to write an exam for the students to complete tomorrow . The exam was going to be on medical terminology . Not too bad I say . I went home , took a shower and changed clothes . Let 's start off with some easy ones . First let me write the directions . Please complete the prefix with the medical term that it signifies . Well , after about an hour . I finished early . I went to the store and bought a light meal and a bottle of merlot . Question: What did the person want to get? Option1: the directions Option2: light meal and bottle of Merlot\nSolution:"
},
{
"from": "gpt",
"value": "light meal and bottle of Merlot"
}
] |
[
{
"from": "human",
"value": "Teacher:Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\nTeacher: Now, understand the problem? Solve this instance: penalty, ticket, jail, fine\nStudent:"
},
{
"from": "gpt",
"value": "police punishment"
}
] |
[
{
"from": "human",
"value": "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\n['2301', 'z', 't', '4149', 'D', '6147', 'O', '2515', 'm', 'T', '8173', 'v', 'T', '6495', 'Z', 'X', 'I', '2515', '5719', 'j', '8697', '9731', 'y', '9297', 'e', '9587', 'e', 'x', 'z', 'j', 'n', 'd', '2067', 'L', '677', '7117', 'a', 'Z', '6819']"
},
{
"from": "gpt",
"value": "2, 3, 5, 7, 9, 10, 12, 13, 15, 16, 17, 20, 23, 25, 27, 28, 29, 30, 31, 32, 34, 37, 38"
}
] |
[
{
"from": "human",
"value": "Teacher: 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n['238', 'h', '92', 'U', '2799']\nSolution: 238, 92, 2799\nReason: Here, the numbers in the input list in order are '238', '92' and '2799'.\n\nNow, solve this instance: ['M', 'j', 'X', '1201', '3513', 'p', '5345', 't', 'A', 'r']\nStudent:"
},
{
"from": "gpt",
"value": "1201, 3513, 5345"
}
] |
[
{
"from": "human",
"value": "Q: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nThe nebulous plan still forming in his mind was looking better and better by the moment.\nA:"
},
{
"from": "gpt",
"value": "Original"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nCraft one correct answer to the question given in input. To make it more interesting, try to use non-stereotypical language if possible. Make sure your correct answer is reasonably long, consistent with the context, and requires common sense (instead of explicit extraction from the context.) In your answer, use as few words as possible from the given context. Use a response that is uncommon/non-stereotypical, so that it is less predictable. To be less repetitive, please vary your language for each question.\n\nContext: \" Yes . I think I had some sort of vision about you . And that is odd for me because I do n't often have visions . Not like that . \nQuestion: What is the sort of vision I had about you ?\nOutput:"
},
{
"from": "gpt",
"value": "I had a sort of dream or waking dream that enabled me to see your future ."
}
] |
[
{
"from": "human",
"value": "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 need to indicate the plausibility of reasoning for the pronoun coreference relations. Each of the provided inputs contains a sentence with a target pronoun and a sentence that justifies which noun phrase the pronoun refers to. Correct reasons do not need to use all the knowledge from the sentence. The resolution of the pronoun coreference relations typically involve one or multiple following knowledge types about commonsense: First: 'Property', the knowledge about property of objects (e.g., ice is cold). Second: 'Object', the knowledge about objects (e.g., cats have ears). Third: 'Eventuality', the knowledge about eventuality (e.g., 'wake up' happens before 'open eyes'). Forth: 'Spatial', the knowledge about spatial position (e.g., object at the back can be blocked). Fifth: 'Quantity', the knowledge about numbers (e.g., 2 is smaller than 10). Sixth: all other knowledge if above ones are not suitable. You should answer 'Correct' if the reasoning made sense, otherwise, you should answer 'Wrong'.\n\nSentence: The city councilmen refused the demonstrators a permit because they feared violence. \n Reason: The 'they' refers to the city councilmen because city councilmen are administrative so they are more likely to fear. \n Question: Is the above reasoning correct or wrong? \nSolution: Correct.\nWhy? This is a correct reason since the pronoun in the sentence is descibed as ones who fear violence and the city councilmen are attached with this property.\n\nNew input: Sentence: Fred watched TV while George went out to buy groceries. After an hour he got back.\n Reason: The 'he' refers to george because he's a male, but not because he's a man. \n Question: Is the above reasoning correct or wrong? \nSolution:"
},
{
"from": "gpt",
"value": "Wrong"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.\nInput: Using our methodology, we tagged 10,000 Arabic tweet dataset for offensiveness, where offensive tweets account for roughly 19% of the tweets. Further, we labeled tweets as vulgar or hate speech. \nOutput:"
},
{
"from": "gpt",
"value": "How many tweets are in the dataset?"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you're given an article, a question which often contains a blank, four options (associated with \"A\", \"B\", \"C\", \"D\") and the answer to that question. Your task is to classify whether the given answer is correct or not by providing \"Yes\" or \"No\", based on the article.\nInput: Article: The Sunset Pasta Cruise to Emerald Bay Saturday evening, September 25, 2010 You will cruise to Emerald Bay at Sunset, one of the most beautiful places in the world while dining on a Pasta Buffet and listening to live light dance music. Buses will pick up Sunset Pasta Cruise diners from the main entrance to the Horizon Casino Resort at: 4:40pm and 5:05pm on Saturday and take you the 1.5 miles to Ski Run Marina for boarding. Boarding is at Ski Run Marina at 5:15 p.m. (with departure at 5:45 p.m.), located in South Lake Tahoe. The cost for the cruise, pasta buffet, live music, and the 2.5-hour cruise to Emerald Bay is $55 (normally $75). The cost for children between 3-11 is $41 and under 3 is free. Must register the under 3 as well for the coast guard count. The Sunset Pasta Cruise will be limited to 200 guests. Large parties will be seated first to insure seating together. Pick up your Sunset Pasta Cruise tickets at the Expo at the Horizon Casino Resort before 3 p.m. on Saturday. Those unclaimed will be sold to those on the waiting list at that time. At approximately 5:45 pm any extra spaces will be sold to passengers on the dock. Children who require a seat must have a ticket as well. Closest lodging to the Pasta Cruise is: Super 8, Lakeland Village. Please note that our sponsor , the Riva Grill, is on the Lake close to the boarding area for the Tahoe Queen. A great gathering place to meet or to have dinner. Call Riva Grill (530) 542-2600 for lunch or dinner reservations while you are visiting Lake Tahoe. \n Question: When will the cruise to Emerald Bay end? \n Options: (A) At about 7:00 pm. (B) At about 8:20 pm. (C) At about 9:20 pm. (D) On Sunday morning. \n Asnwer: B\nOutput:"
},
{
"from": "gpt",
"value": "Yes"
}
] |
[
{
"from": "human",
"value": "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 are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\n\n['238', 'h', '92', 'U', '2799']\nSolution: 3\nWhy? Here, the numbers in the input list are '238', '92' and '2799', hence their count is 3.\n\nNew input: ['n', 'V', 'N', 'o', '2681']\nSolution:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "Definition: In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.\nInput: This symphony's final movement includes a collaboration between a flute and a piccolo, meant to represent an ominous bird. The composer of this symphony included a notation asking for \"the largest possible contingent of strings.\" Its second movement, marked Andante moderato, is an A-flat major landler. This symphony is intended to be played with a five-minute pause after its first movement, which re-used its composer's abandoned piece (*) Totenfeier. It calls for a mezzo-soprano voice in its fourth movement, Urlicht, and includes a setting of Das Knaben Wunderhorn. This symphony in C minor was inspired by a Klopstock poem heard at a funeral that includes the line \"Rise again, yes, rise again.\" For 10 points, name this second symphony by Gustav Mahler.\nOutput:"
},
{
"from": "gpt",
"value": "Fine Arts"
}
] |
[
{
"from": "human",
"value": "In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \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 argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \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 argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\nOne example is below.\nQ: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 } = true\nA: select the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.\nRationale: Here, the generated sentence interprets given logical form correctly that 3rd maximum should be selected from given table rows.\nQ: and { only { filter_eq { all_rows ; competition ; 2014 fifa world cup qualification } } ; eq { hop { filter_eq { all_rows ; competition ; 2014 fifa world cup qualification } ; date } ; 23 march 2013 } } = true\nA:"
},
{
"from": "gpt",
"value": "select the rows whose competition record fuzzily matches to 2014 fifa world cup qualification . there is only one such row in the table . the date record of this unqiue row is 23 march 2013 ."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, a passage will be given and the goal is to generate a question about temporal relations based on that passage. A temporal relation describes the relation between two things with respect to time e.g., something happens/starts/terminates/... immediately/shortly/usually/... before/after/during/... something else.\n Your question should include an event, or ask about an event, and should not be a yes/no question.\nQ: Passage: Sale of the 2002 book co-written by the former Russian spy Alexander Litvinenko who died of suspected radioactive poisoning are selling on the Internet at up to 30 times their orginal price. Two copies of \"Blowing Up Russia: Terror from Within\" are currently available on the British online book store Amazon for 189 pounds (280 euros, 374 dollars) for a new version and nearly 237 for a second-hand edition.\nA:"
},
{
"from": "gpt",
"value": "What event has already finished?"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task you are given a sentence. You must judge whether the object of the main clause is singular(like: apple) or plural(like: apartments). Label the instances as \"Singular\" or \"Plural\" based on your judgment.\nTeacher: Now, understand the problem? Solve this instance: All the new electric cars needed effective storage batteries to be practical, as well.\nStudent:"
},
{
"from": "gpt",
"value": "Plural"
}
] |
[
{
"from": "human",
"value": "In this task you are given a list of integers and you need to find the absolute value of the difference between each two consecutive values. The output should be a list of the absolute value of the differences of each two consecutive values.\n\nExample input: [7, 1, 5, 8, -4]\nExample output: [6, 4, 3, 12]\nExample explanation: The output is a list of the absolute value of the differences of every two consecutive values. So this is a good example.\nQ: [87, 57, 78, 72, -35, 10]\nA:"
},
{
"from": "gpt",
"value": "[30, 21, 6, 107, 45]"
}
] |
[
{
"from": "human",
"value": "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: socks. \nQuestion: I had to buy a new pair of socks for the game but not shoes since the _ had holes in them. \nAnswer: socks.\n\nEx Output:\nI had to buy a new pair of socks for the game but not shoes since the _ were intact.\n\n\nEx Input:\nContext 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\nEx Output:\nKyle's boss gave him the pen to use instead of the pencil because the _ was harder to read.\n\n\nEx Input:\nContext Word: island. \nQuestion: On the island the weather was frequently unpredictable. It was supposed to rain this weekend and the _ would get very wet. \nAnswer: island.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "On the island the weather was frequently unpredictable. It was supposed to rain this weekend and the _ would be very heavy.\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\n\nInput: Consider Input: [309, -658, -583]\n\nOutput: [310, -660, -580]\n\n\nInput: Consider Input: [309, -204, 555, -5]\n\nOutput: [310, -200, 560, 0]\n\n\nInput: Consider Input: [638, 820, 854, 284, 606, -769, 167, 215, 612, 581, -407, 726, -778, -382, 340]\n\n"
},
{
"from": "gpt",
"value": "Output: [640, 820, 850, 280, 610, -770, 170, 220, 610, 580, -410, 730, -780, -380, 340]\n\n\n"
}
] |
[
{
"from": "human",
"value": "Compose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any.\n\nLet me give you an example: original question: Who is the museum director of [Science Museum, London]?\nanswer: Ian Blatchford\nanswer type: Museum director. \nauxiliary information: The Science Museum is a major museum on Exhibition Road in South Kensington, London. It was founded in 1857 and today is one of the city's major tourist attractions, attracting 3.3 million visitors annually. Like other publicly funded national museums in the United Kingdom, the Science Museum does not charge visitors for admission. Temporary exhibitions, however, may incur an admission fee. It is part of the Science Museum Group, having merged with the Museum of Science and Industry in Manchester in 2012.\nThe answer to this example can be: The museum director of the [Science Museum, London] is?\nHere is why: The question is correctly paraphrased in this example.\n\nOK. solve this:\noriginal question: What is the rocket status of rocket [Energia]?\nanswer: retired\nanswer type: Rocket Status.\nauxiliary information: Energia was a Soviet rocket that was designed by NPO Energia to serve as a heavy-lift expendable launch system as well as a booster for the Buran spacecraft. Control system main developer enterprise was the NPO \"Electropribor\". The Energia used four strap-on boosters each powered by a four-chamber RD-170 engine burning kerosene/LOX, and a central core stage with 4 one-chamber RD-0120 engines fueled by liquid hydrogen/LOX. The launch system had two functionally different operational variants: Energia-Polyus, the initial test configuration, in which the Polyus system was used as a final stage to put the payload into orbit, and Energia-Buran, in which the Buran spacecraft was the payload and the source of the orbit insertion impulse. The rocket had the capacity to place about 100 tonnes in Low Earth orbit, up to 20 tonnes to geostationary orbit and up to 32 tonnes to a translunar trajectory.\nAnswer:"
},
{
"from": "gpt",
"value": "How would you categorize the rocket status of the rocket known as [Energia]?"
}
] |
[
{
"from": "human",
"value": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.\n\nExample input: Beginning: Butch had a really old computer. Middle 1: Butch decided to order a new computer online. Middle 2: Butch noticed that a storm was approaching to his town. Ending: It arrived and Butch was much happier.\nExample output: 1\nExample explanation: People generally don't feel happy about natural disasters like storms. Therefore, we choose 1 in this case.\nQ: Beginning: My sister in law contacted me yesterday. Middle 1: My sister in law told me her paintings were only worth a few dollars. Middle 2: She told me her paintings were worth millions. Ending: She was disappointed and decided not to sell them.\nA:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a question and an answer, you would be asked to create the sentence based on the Question-Answer provided. It should be contained within the Question-Answer provided.\nProblem:Question: What is the term for the movement of molecules from an area of high concentration to an area of low concentration? Answer: diffusion\nSolution:"
},
{
"from": "gpt",
"value": "Diffusion is the term for the movement of molecules from an area of high concentration to an area of low concentration."
}
] |
[
{
"from": "human",
"value": "In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\n\n[Q]: Article: In February 2006, Lydia Angyiou and her two sons were walking through their village in northern Canada. The sound of children shouting made her turn around. To her horror, Lydia saw a 700-pound polar bear behind her eyeing her seven-year-old son. Getting between the bear and her child, Lydia yelled at the children to run away. She then began hitting and kicking the animal as hard as she could. A neighbor who heard all the noise came and shot the bear. But everyone agreed it was Lydia who had saved her children's lives. A local policeman described it this way: \"... I guess when your back is up against the wall, ... we come up with super-human strength.\" Where does this \"super-human strength\", courage and quick thinking come from? Experts say it comes from stress! In stressful situations, the body releases chemicals that prepare it to take action. These chemicals give people the speed and strength they need to fight danger or run away from it. When we think of stress, we usually think of its negative effects. Studies, though, show that moderate levels of stress are actually helpful. In fact, the way we perform is usually affected by the amount of stress we feel. Stress causes the brain to release adrenaline which in turn increases our energy and excitement. The chemical gives us clearer minds and helps us to do more. This is why some people say they work better under a deadline. Adrenaline that is not released for long periods of time can cause us to increase and strengthen our abilities instead of weakening them. We sometimes turn out our very best work when we push ourselves to the limit. Stress can also make us more confident. Handling small amounts of stress now prepares us for handling serious situations in the future. Who knows? Today's stress may even prepare for the next polar bear that comes along! \n Answer: You are cornered.\n[A]: What does the policeman probably mean by saying \"your back is up against the wall\"?\n\n\n[Q]: Article: By Zhang Youlv (China Daily 09/29/2008)--A manned lunar landing is China's next target when the current three-stage space program ends in the next dacade. \"When our manned space program is completed, we will travel even further,\" Wang Zhaoyao, deputy head of China's manned space program office and Shenzhou VII mission spokesman, told a briefing in Beijing three hours after China's third manned space mission was successfully concluded yesterday. \"After comprehensively analyzing the general trend of the international development of manned space, as well as realities in China, we see a manned lunar landing as a both challenging and tactical field in global hi-tech,\" he said. \"We believe it necessary for our country to do something in this field,\" Wang said. He did not give a specific date for a moon landing. Wang, however, said, \"Experts believe this is 'very much needed' for research into relevant (closely connected) technologies to further China's achievements in space.\" The 68-hour Shenzhou VII mission featured a 25-minute spacewalk on Saturday. It was broadcast live and watched by millions throughout the country. The crew's landing at a site in the Inner Mongolia autonomous region was also carried live by national television. The entire mission was pronounced a complete success. Wang said the three astronauts, were transported to Hohhot, the region's capital, and would spend the evening there. \"They will return to Beijing this morning,\" he said. \"During the course of the mission, Russian experts provided strong technical support for the EVA spacesuits. The successful Sino-Russian cooperation for this flight created beneficial conditions for more intensive cooperation between the two sides in the future,\" Wang said. The mission's success has paved the way for completing the second stage of the program--building a space station before 2020. Before that, a space lab will be set up in 2010 with Shenzhou X, the country's next full-crew space journey. \n Answer: No specific date.\n[A]: When will China's spaceship land on the moon?\n\n\n[Q]: Article: If you have ever experienced jet lag ,you know how much of a drag it can be. Jet lag happens as a result of air travel, when traveling between two or more time zones. Your body is used to operating in a certain time zone, and when its timing is affected, you're likely to have problems. Edward Norton's character in the movies Fight Club faces the struggle of jet-lag-induced sleeplessness due to his constant traveling. Sleeplessness is just one of the effects of jet lag, and it can lead to other problems, such as tiredness, memory loss and confusion. That's not something you should have to fight on a business trip and it certainly won't make your vacation very enjoyable, either. Sleeplessness is the biggest problem for travelers that suffer from jet lag. Don't worry. You can do something to prevent it. Modify Your Body Clock To prevent the effects on your body's timing that come with crossing time zones, you need to change your body clock sooner, rather than later. You can do this by putting yourself on the same time as your destination time zone before you fly. If you know that you will be traveling to London from the eastern United States, you'll have a five-hour time difference to deal with. Plan for it. Avoid Heavy Food and Alcohol Part of the pleasure of flying commercially, especially if you fly business or first class, is taking advantages of the food and drinks. If you want to avoid jet lag, though, you should think twice. Eating heavy food will only make the jet lag worse. It isn't good to drink alcohol during a flight, either, because it may make you drowsy. Wait until your body adjusts before you decide to have heavy food or drink alcohol. \n Answer: How jet lag happens and tips on traveling safely.\n[A]:"
},
{
"from": "gpt",
"value": "What is the main idea of the passage?\n\n\n"
}
] |
[
{
"from": "human",
"value": "instruction:\nIn this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.\nquestion:\n[-16, 67, -56, 69, 26, 66]\nanswer:\n1\n\n\nquestion:\n[-99, 6, 36, -88]\nanswer:\n11\n\n\nquestion:\n[40, -61, -2, 20]\nanswer:\n"
},
{
"from": "gpt",
"value": "20\n\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: toxic and non-toxic. Toxicity is defiend as anything that is rude, disrespectful, or unreasonable that would make someone want to leave a converation.\nTeacher: Now, understand the problem? Solve this instance: Comment: As others have pointed out, you could have literally hundreds of cyclists (or thousands of pedestrians) using a roadway before you did as much damage as a single car. The shift wasn't merely a change in volume, but towards a form of transportation that demanded, by its nature, near-exclusive use of the right-of-way; needed unprecedented investments in infrastructure to be viable; and which, as mentioned, resulted in ballooning maintenance costs.\n\nAlso, I think you underestimate the volume of traffic before the advent of cars. Congestion was an urban issue long before the Industrial Revolution. Urbanization pre-automobile made it worse. A busy NYC street in 1903, for instance, likely contained more people than could fit on a modern roadway, since single-occupancy vehicles make inefficient use of space.\n\nThe bottom line is cars cost the public in unique ways; gas taxes and motor vehicle fees were initiated in a conscious acknowledgment of that. Bikes weren't omitted as an oversight.\nStudent:"
},
{
"from": "gpt",
"value": "Non-toxic"
}
] |
[
{
"from": "human",
"value": "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 need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence.\n\nSentence: 'a white cat on a desk near a computer monitor'. Count the number of vowels in the given sentence.\nSolution: 16\nWhy? This sentence has 5 occurrences of letter 'a', 4 of 'e', 2 of 'i', 4 of 'o', and 1 of 'u'. This adds up to 16. So, the answer is 16.\n\nNew input: Sentence: 'a bedroom with a bed, dresser, and chest of drawers'. Count the number of consonants in the given sentence.\nSolution:"
},
{
"from": "gpt",
"value": "26"
}
] |
[
{
"from": "human",
"value": "Definition: Given a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).\nInput: Suppose -2 = 2*f - 16. Suppose -10 - 19 = -3*x - 5*j, -f = -x - j. Calculate the remainder when x is divided by 2.\nOutput:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.\nExample: Ok, the national drink of Scotland is whisky.\nOutput: assistant\nIt is pretty straightforward. It is knowledge sharing, and the assistant explains the question asked by the user.\n\nNew input case for you: thank you, can you tell me more about the history here?\nOutput:"
},
{
"from": "gpt",
"value": "user"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e tagset of this corpus is - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, \n 'PRT': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, \n 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nSee one example below:\nProblem: Sentence: David A. DiLoreto , president of metal container division , was named *-1 to the additional post of group vice president , packaging products , at this packaging {{ , }} industrial and aerospace products concern , *-1 succeeding Delmont A. Davis , who *T*-3 was named *-2 president and chief operating officer in August . \nWord: ,\nSolution: .\nExplanation: ',' is assigned the period (.) symbol since it denotes a punctuation.\n\nProblem: Sentence: Heritage Media Corp. , New York , said 0 it offered *-2 to buy {{ the }} shares of POP Radio Corp. 0 it does n't already own *T*-1 in a stock swap . \nWord: the\nSolution:"
},
{
"from": "gpt",
"value": "DET"
}
] |
[
{
"from": "human",
"value": "Teacher: Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. \nTeacher: Now, understand the problem? If you are still confused, see the following example:\nnews:According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing .\npolarity:neutral\nSolution: true\nReason: Although the author uses negative words like 'no' in the news, there is no evidence of the news begin positive or negative for any stakeholder. Hence, the polarity is neutral and the output is True.\n\nNow, solve this instance: news:As an overall effect of the above-mentioned measures Glaston will recognize non-recurring expenses of EUR 12 million in the fourth quarter of 2008 .\npolarity:negative\nStudent:"
},
{
"from": "gpt",
"value": "false"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task you will be given a list of strings and you need to concatenate them.\nInput: ['m', 'two', 'n', 'w', 'to', 'y', 'z', 'N', 'It', 'U']\nOutput:"
},
{
"from": "gpt",
"value": "mtwonwtoyzNItU"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task you are given a tweet and you must identify whether the tweet contains any offense or any form of (untargeted) profanity. Label the post as NOT if the post does not contain offense or profanity. Non-offensive posts do not include any form of offense or profanity. label the post as OFFENSIVE if the post contains offensive language or a targeted (veiled or direct) offense. Twitter user mentions were substituted by @USER and URLs have been substitute by URL.\nInput: @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER @USER mine I tell him if you act like antifa I will knock your block...you wanna get bad...i dont care how handicap I will take you down\nOutput:"
},
{
"from": "gpt",
"value": "NOT"
}
] |
[
{
"from": "human",
"value": "In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words.\n\nLet me give you an example: Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!\nThe answer to this example can be: crooler\nHere is why: In this example, the number two refers to something that the word: crooler.\n\nOK. solve this:\nVegeta: For thousands of years I have laid dormant , who has disturbed my ...\nGoku: Hey , best buddy !\nVegeta: ... Oh , it 's you . Explain , idiot .\nTrunks: No , no , no ...\nGoku: We found three more Androids !\nTrunks: DA - HA - MIT !\nVegeta: Three whole Androids , huh , pretty sure that makes _ eight _ . Never lietting the boy live this one down ...\nAnswer:"
},
{
"from": "gpt",
"value": "Androids"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good.\nInput: Unfortunately on the first use, popcorn went everywhere. Gave it another go, and even more unfortunately on the second use (one week later), the machine burnt the popcorn!\nOutput:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "instruction:\nYou are given an original reference as well as a system reference. Your task is to judge the quality of the system reference. If the utterance is grammatically correct and fluent output 1, else output 0.\nquestion:\nSystem Reference: red door cafe has cheap prices and the phone number is 4152828283.\nOriginal Reference: the red door cafe is cheap. their phone number is 4152828283.\nanswer:\n1\n\n\nquestion:\nSystem Reference: what area would you like the restaurant to be in?\nOriginal Reference: in which area are you looking for restaurant -s?.\nanswer:\n1\n\n\nquestion:\nSystem Reference: x is a chinese restaurant in the city centre and riverside area near x.\nOriginal Reference: x is a chinese restaurant in the city centre and riverside areas near x.\nanswer:\n"
},
{
"from": "gpt",
"value": "1\n\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nTeacher: Now, understand the problem? Solve this instance: Middle: i thought the person was going to rob me. Ending: While being confused, I gave him some directions.\nStudent:"
},
{
"from": "gpt",
"value": "Someone came into my restaurant around night time."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nSee one example below:\nProblem: He poured out his to heart God, and after a few minutes the need left him, for a while anyway.\nSolution: Inversion\nExplanation: \"heart\" and \"to\" have been inverted.\n\nProblem: There are another two thousand in reserve, hidden in the forest.\nSolution:"
},
{
"from": "gpt",
"value": "Original"
}
] |
[
{
"from": "human",
"value": "In this task, you are given a context sentence containing a blank (_). You are expected to fill the blank with one word to make the sentence convey a cultural anti-stereotype. Anti-stereotype is an idea that goes against a common belief about a particular group of people. Your answer must not contain more than one word.\n\nContext: The bartender was very _ towards his customers."
},
{
"from": "gpt",
"value": "quiet"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\nProblem:I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN I_TURN_LEFT I_RUN\nSolution:"
},
{
"from": "gpt",
"value": "turn around right thrice and run around left"
}
] |
[
{
"from": "human",
"value": "In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\n\n[EX Q]: Fact1: Producers make food from inorganic molecules., Fact2: Autotrophs absorb sunlight energy and transfer inorganic mineral nutrients into organic molecules., Question: What do producers turn sunlight into? (A) energy (B) apples (C) heat (D) paper (E) drinks (F) waste (G) inorganic goods (H) food\n[EX A]: H\n\n[EX Q]: Fact1: Active immunity results when an immune response to a pathogen produces memory cells., Fact2: Vaccination is Active Acquired Immunity., Question: What results when an immune response to a pathogen produces memory cells? (A) anemia (B) vaccination (C) kill them (D) competition (E) lie detectors (F) rapid expansion (G) killing insects (H) it needs them\n[EX A]: B\n\n[EX Q]: Fact1: an aquatic animal requires great amounts of water to survive, Fact2: Too much algae can deplete the water of oxygen, making it impossible for aquatic animals to survive., Question: an aquatic animal requires not having too much what in water? (A) warmth (B) Energy. (C) energy (D) fats (E) algae (F) matter (G) harm (H) sodium\n[EX A]:"
},
{
"from": "gpt",
"value": "E\n\n"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: Given an English language product review, determine if it is a Good Review or a Bad Review. A good review is one where the product's review has positive tone and Bad review is one where the tone of product's review is negative.\nPROBLEM: This lamp does work. A little tricky on installation, but...works. Unfortunately it's not as bright as you would hope. Not a terrible light.\n\nSOLUTION: Bad review\n\nPROBLEM: Just got my copy in the mail this morning and am going to return it as soon as possible. The song quality is very poor compared with past albums of his by far. I know he put a lot into the recording process on these cd's but its definitely not worth the cost. There are many other artists out there who can produce real country music that you would think we all listen to. This release does NOT belong in any country.\n\nSOLUTION: Bad review\n\nPROBLEM: Love making these with our little grandchild. We can cut two or more sizes at once. It doesn't stick after baking but we wait overnight for ready time.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "Good Review\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given two pieces of text with the same meaning. One of them is simpler and easier to understand for non-native English speakers. Complex texts may contain more difficult words, have unnecessary phrases or contain long sentences. Your task is to choose the simpler piece of text. You are expected to output 'Text one' if the first sentence is simpler. Otherwise output 'Text two'.\nExample: Text one: From its inception, it was designated a duty-free port and vied with the neighboring Sultanate of Pattani for trade\n Text two: From the start, it was chosen to be a duty-free port to compete with the neighboring Sultanate of Pattani for trade.\nExample solution: Text two\nExample explanation: Text two has simpler words, ,so it is easier to understand by non-native English speakers.\n\nProblem: Text one: They are most often like a storm, that is, associated with a localized low-pressure region within a severe thunderstorm.\n Text two: They are most often like a storm, that is, associated with a localized low-pressure region within a severe thunderstorm.\n"
},
{
"from": "gpt",
"value": "Solution: Text one"
}
] |
[
{
"from": "human",
"value": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\n--------\nQuestion: Passage: Every evening I like to wash a load of laundry for one of the members of our family . Tonight I washed a load of my son 's clothes in the washing machine with an extra strong tough stain remover and detergent . When the load was done washing , I moved the wet clothes to the dryer and closed the door . I removed the lint collector from the top of the dryer and pulled the lint off of the lint screen . The load of clothes I was washing needed to dry on high temperature , so I selected the appropriate setting and pushed start on the dryer . It took seventy minutes for my clothes to be dry . At that time , I removed them from the dryer and folded them for my son to put away in his dresser . Question: When did they replace the lint collector in the dryer slot? Option1: before washing the clothes Option2: after cleaning the lint collector\n\nAnswer: after cleaning the lint collector\n\n\nQuestion: Passage: After I have played outside with my sister and rolled in the dirt , slid down the slide and threw balls at each other , we picked up a lot of dirt and sweat that my sister and I just could not wipe clean . We get in the house and decide who should go to shower first . We go to our rooms and peel off all the sticky and yucky clothes and gather our clean clothes and underwear . My sister goes first . We both know to step in carefully , get our wash clothes and soap . A fresh shower with shower and water we know will wash away all the grime from our bodies and hair . We made sure we had clean towels to dry off . Question: What does she do with the water? Option1: clean her body Option2: wash her clothes\n\nAnswer: clean her body\n\n\nQuestion: Passage: I decided to go shopping for clothes , specifically , casual shirts . I 'm not a big fan of clothes shopping , because it 's not usually as easy as seeing something and just paying for it . I found the area where the shirts were that would be my size . Unfortunately it was being used . I shopped around for a little while longer until the dressing room was empty . I went into the room and took off the shirt I was wearing so I could try on the three shirts I had brought in . I knew there were other people wanting to use the dressing room , and I always get stressed when I know other people are in line behind me and waiting for me to finish . The three shirts fit , and I took them to the cashier to pay and get out of there . Question: What would they do if the shirts did not fit right? Option1: pay for the shirts Option2: Put the shirts back\n\nAnswer:"
},
{
"from": "gpt",
"value": "Put the shirts back\n\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher:Given a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).\nTeacher: Now, understand the problem? Solve this instance: What is -2 - (-2 + -1 - -2)?\nStudent:"
},
{
"from": "gpt",
"value": "-1"
}
] |
[
{
"from": "human",
"value": "Write an incorrect answer to the given question based on the associated fact. You are also provided with the correct answer to the given question. Make sure that your incorrect answer is relevant and similar to the associated fact. Also, try to make the incorrect answer similar to the correct answer so that distinguishing the correct answer from the incorrect answer is not very easy. Make sure you don't accidentally provide another correct answer! Also, make sure they sound reasonable (e.g., might be on a school pop quiz). A good incorrect answer can be constructed using words associated with the question, but not the correct answer. For example, for the question \"What helps plants survive?\", using words like \"weeds\", \"vase\", \"bee\" (associated with \"plant\"), or \"first aid\", \"parachute\", \"accident\" (associated with \"survive\") etc. Your incorrect answers make the question hard, so these results in good incorrect answers.\n\nLet me give you an example: Fact: pesticides can harm animals. \nQuestion: What can harm animals? \n Correct Answer: pesticides.\nThe answer to this example can be: pet shampoo.\nHere is why: This is clearly an incorrect answer to the question. And since, it is relevant with the given fact, it is a good incorrect answer. Other good incorrect answers are \"fresh water\" and \"clouds\".\n\nOK. solve this:\nFact: DNA passes traits from parents to offspring. \nQuestion: What passes traits from parents to offspring? \nCorrect Answer: DNA.\nAnswer:"
},
{
"from": "gpt",
"value": "Birth certificate."
}
] |
[
{
"from": "human",
"value": "You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: *a phras from sentence 1e* 2: *a phras from sentence 2* 3: *a phrase from sentence 3*\n\n[Q]: 1: ( CNN ) From the community of Montoursville , Pennsylvania , U.S.A . , to the community of Haltern am See , Germany : . 2: We offer our heartfelt condolences for the pain you must be feeling at this time after the loss of 16 students and two teachers in the horrendous crash of Germanwings Flight 9525 . 3: Haltern am See , Germany , lost 16 students and 2 teachers in Germanwings Flight 9525 .\n[A]: 1: the community of Haltern am See , Germany 2: you 3: Haltern am See , Germany\n\n\n[Q]: 1: After Don Bradman , there has been no Australian player more famous than Richie Benaud , Cricket Australia said on its website . 2: Benaud stood at the top of the game throughout his rich life , first as a record-breaking leg-spinner and captain , and then as cricket 's most famous -- and most impersonated -- broadcaster . 3: Richie Benaud first earned fame as a cricket player , later as broadcaster .\n[A]: 1: Richie Benaud 2: Benaud 3: Richie Benaud\n\n\n[Q]: 1: For example , we have gone from 89 cents in our rainy day fund and an $ 8 billion shortfall to now having one of the nation 's strongest state budgets and a nearly $ 2 billion surplus . 2: We've gone from losing 350,000 private-sector jobs to creating about 340,000 new ones . 3: He says Ohio has gone from a budget deficit to surplus , from losing jobs to creating them .\n[A]:"
},
{
"from": "gpt",
"value": "1: we 2: We've 3: Ohio\n\n\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given an article, a question which often contains a blank, four options (associated with \"A\", \"B\", \"C\", \"D\") and the answer to that question. Your task is to classify whether the given answer is correct or not by providing \"Yes\" or \"No\", based on the article.\nArticle: History is full of cases where dreams have been a pathway to creativity and discovery. A striking example is provided by Dr. Otto Loewi, a pharmacologist and winner of a Nobel Prize. Loewi had spent years studying the chemical transmission of nerve impulses . A major breakthrough in his research came when he dreamed of an experiment three nights in a row. On the first two nights he woke up and wrote down the experiment quickly and untidily on paper. But the next morning, he couldn't tell what the notes meant. On the third night, he got up after having the dream. This time, instead of making notes he went straight to his laboratory and performed the important experiment. Loewi later said that if the experiment had occurred to him while awake he would not have given it another thought. Loewi's experiment gives some insight into using dreams to produce creative solutions. Nervous feelings are reduced during dreaming, which may be especially useful in solving problems that require a fresh point of view. Being able to take advantage of dreams for solving is improved if you \"set\" yourself before sleeping. Before you go to bed, try to think intently about a problem you wish to solve. Bury yourself in the problem by stating it clearly and reviewing all relevant information. Then use the suggestions listed in the previous section to catch your dreams. Although this method is not guaranteed to produce an original solution or a new insight, it is certain to be an adventure. About half of a group of college students using the method for a week recalled a dream that helped them solve a personal problem.www.ks5u.com \n Question: Through Loewi's experiment, the author tries to prove that _ . \n Options: (A) very little is really known about the meaning of dreams (B) dreams can be useful in producing creative solutions to one's problems (C) it is possible to \"catch\" one's dreams by planning before going to sleep (D) it helped in the study of transmission of nerve impulses \n Asnwer: A\nA:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "Q: In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\nthreefiveeightfourzerofivezerozerosixninefive\nA:"
},
{
"from": "gpt",
"value": "35840500695"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a review from Amazon and rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good. Your task is to generate whether the rating matches the review or not. Answer with \"True\" if the sentence belongs to that section, otherwise answer with \"False\"\n\nExample Input: Review: I have been looking for a low price smart watch, and I finally found one. It not only tracks fitness, and heart rate, but it notifies me when I have a call or text. Something that not all of the fitness watches do.. \n Rating: 1\nExample Output: False\n\nExample Input: Review: I am happy with my purchase, I needed a lunchbox for my son and couldn't find anything that wasn't \"girly\" in the store. I have used the Packit brand for the past 5 years for my daughter so I knew what I wanted for my son. \n Rating: 1\nExample Output: False\n\nExample Input: Review: Looks cheap. He didnt care of course. He liked it. But I prefer to wear things that look and feel of quality. It also runs large. Overall, waste of $$ \n Rating: 1\nExample Output:"
},
{
"from": "gpt",
"value": "True\n\n"
}
] |
[
{
"from": "human",
"value": "The task is to generate text based of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons emotional reaction to the event, i.e. how that person feels after doing the action.\n\nLet me give you an example: PersonX does PersonX's job well\nThe answer to this example can be: accomplished by their actions\nHere is why: this is a good example because PersonX will likely feel accomplished by doing their job well.\n\nOK. solve this:\nPersonX spends some time together\nAnswer:"
},
{
"from": "gpt",
"value": "happy and comfortable"
}
] |
[
{
"from": "human",
"value": "You are given a math word problem and you are supposed to only use subtraction on the numbers embedded in the text to answer the following question and then only report the final numerical answer.\nOne example is below.\nQ: Context: Sam is 6 feet tall and Alex is 5 feet tall \n\n Question: By how many feet is Sam taller than Alex? \nA: 1\nRationale: Sam's height - Alex's height = 6-5 = 1\nQ: Context: There were 13 roses in the vase. Jessica cut some more roses from her flower garden which had a total of 12 roses. There are now 21 roses in the vase. \n\n Question: How many roses are left in the garden?\nA:"
},
{
"from": "gpt",
"value": "4"
}
] |
[
{
"from": "human",
"value": "A ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.\n--------\nQuestion: x = 2, equation weights = [6, 3, 7]\n\nAnswer: 37\n\n\nQuestion: x = 3, equation weights = [5, 9, 2]\n\nAnswer: 74\n\n\nQuestion: x = 6, equation weights = [5, 8, 9]\n\nAnswer:"
},
{
"from": "gpt",
"value": "237\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.\n\nSentence 1: people dressed in green and white dancing Sentence 2: People dancing during a St. Patricks day parade.\n"
},
{
"from": "gpt",
"value": "N"
}
] |
[
{
"from": "human",
"value": "Given a sentence in Dutch, generate a new Dutch sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\n\nEx Input:\nMensen worden wakker als de zon kookt.\n\nEx Output:\nMensen worden wakker als de zon spreekt.\n\n\nEx Input:\nDe dominee hield de achterkant in de gaten.\n\nEx Output:\nDe minister keek naar de verhuizing.\n\n\nEx Input:\nOp je trouwdag zou je zeggen dat je van je vrouw houdt.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "Op je mobiel zou je zeggen dat je je vrouw belt.\n\n\n"
}
] |
[
{
"from": "human",
"value": "Categorize the following sentence into one of the five different emotions: anger, confusion, joy, sadness and neutral.\n\n[Q]: \"They hated [NAME] because he told them the truth.\"\n[A]: neutral\n\n\n[Q]: I love how the dog is just happy the cat is giving him attention.\n[A]: joy\n\n\n[Q]: im glad they have it but this should have really been introduced in DMC3\n[A]:"
},
{
"from": "gpt",
"value": "joy\n\n\n"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you need to count the number of words in a sentence that end with the given letter. Answer with numbers and not words.\nSentence: 'a man and woman ride a horse carriage on top of cobble stones'. How many words end with the letter 'a' in the sentence.\nA:"
},
{
"from": "gpt",
"value": "2"
}
] |
[
{
"from": "human",
"value": "In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\n\nEx Input:\nSentence1: 'horse with a rider walking across a stream', Sentence2: 'a heard of elephants with their backs turned'. Is the frequency of the word 'of' in two sentences equal?\n\nEx Output:\nNo\n\n\nEx Input:\nSentence1: 'people playing a game in a wood gated field', Sentence2: 'a teddy bear sits next to a small pair of black boots'. Is the frequency of the word 'a' in two sentences equal?\n\nEx Output:\nYes\n\n\nEx Input:\nSentence1: 'a driver holds the wheel of the vehicle with one hand while text messaging on a mobile phone with the other', Sentence2: 'back view of a zebra walking through the grass'. Is the frequency of the word 'a' in two sentences equal?\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "No\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given two natural language statements with similar wording. You must choose the statement that makes less sense based on common sense knowledge. A '\n' separates the statements. Use \"first\" or \"second\" to indicate which sentence makes less sense.\nQ: Mountains from Poland are very high\nBeaches from Poland are very high\nA:"
},
{
"from": "gpt",
"value": "second"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a phrase describing the relationship between two words, extract the words and the lexical relationship between them. The relation has to be of the type 'MemberOf', 'MadeOf', 'Synonym', 'Entails', 'HasA', 'HasProperty', 'PartOf', 'Antonym' or 'IsA'. The output should have the format: word1 relation word2.\nSee one example below:\nProblem: account can be used with the same meaning of report\nSolution: account Synonym report\nExplanation: The output is correct as the input describes the relationship between account and report, and the relation is that of having the same meaning, therefore they have a Synonym relationship.\n\nProblem: snowflake is a kind of ice\nSolution:"
},
{
"from": "gpt",
"value": "snowflake IsA ice"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\".\nExample: Katrina gave Christine a stuffed animal for their birthday, but _ already had this one. (A) Katrina (B) Christine\nOutput: B\nSince the blank is someone who received the gift and already had a stuffed animal, the answer must be \"Christine\".\n\nNew input case for you: The summer camp counselor, Amy, gave lessons to Katrina because _ was a great instructor. (A) Amy (B) Katrina\nOutput:"
},
{
"from": "gpt",
"value": "A"
}
] |
[
{
"from": "human",
"value": "Q: You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'.\nPremise: Growth and Development of Bones Early in the development of a human fetus, the skeleton is made entirely of cartilage. \n Hypothesis: Early in the development of a human fetus, the skeleton is made entirely of cartilage.\nA:"
},
{
"from": "gpt",
"value": "entails"
}
] |
[
{
"from": "human",
"value": "Q: You will be given a person's personality, and a history of a conversation this person has had. You will be given four candidate sentences to complete the conversation, based on the context. Choose one and answer with the text.\nPersonality: A hobby of mine is the drums.\nOne of my favorite artists is drake.\nI also enjoy cooking.\nI like to go out to eat.\nChat history: -Hi, I just finished listening to Drake. What do like doing?\n -How are you doing tonight.\n -I like messing around on the drums.\n -I like to play sport and baking.\n -I really like cooking too. Going out to eat is also a fun thing.\n -It is so sad what happen in Fl.\n -You mean with the hurricane?\n -Yes my son was with his dad in Fl when it all happen.\nCandidates 1) Cooking. I'm a big foodie. 2) Did they get flooded at their place? 3) I'm a girl and I've several girls of own. 4) Yeah I do, its a lot of fun.\nA:"
},
{
"from": "gpt",
"value": "Did they get flooded at their place?"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a fact statement and question based on the fact. Your task is to generate the correct answer for the question. The answer needs to be generated using the context fact statement.\nSee one example below:\nProblem: Fact: deep sea animals live deep in the ocean. Question: Frilled sharks and angler fish live far beneath the surface of the ocean, which is why they are known as?\nSolution: Deep sea animals\nExplanation: This is the correct answer since the fact says that deep sea animals live deep in the ocean and the question asks for what fish who live deep in the ocean are called.\n\nProblem: Fact: dead organisms rot. Question: Dead organisms, like trees provide?\nSolution:"
},
{
"from": "gpt",
"value": "thriving communities"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.\n--------\nQuestion: yffyytttff\n\nAnswer: yffy\n\n\nQuestion: fmmnnmmfmnfm\n\nAnswer: fmmnnmmf\n\n\nQuestion: wkwkwwkwwwwkk\n\nAnswer:"
},
{
"from": "gpt",
"value": "wkwwkw\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list (\"[]\") should be returned. Otherwise, answer with the list of whole numbers separated by comma inside brackets.\nQ: [54.442, -46.478, 2.091, 21.202, -55.26, 21.172, 13.972, 20]\nA: "
},
{
"from": "gpt",
"value": "[20]"
}
] |
[
{
"from": "human",
"value": "In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nExample: Middle: Helen planned to drive to Canada but it started snowing heavily. Ending: Helen stayed home instead and planned to go another day.\nExample solution: Helen lived in America.\nExample explanation: Mention of the destination country name and driving implies that Helen is from a nearby foreign country.\n\nProblem: Middle: we decided to go to a chess tournament. Ending: It was a fun trip but we never went back.\n"
},
{
"from": "gpt",
"value": "Solution: A group of us play chess at work."
}
] |
[
{
"from": "human",
"value": "In 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.\n\nInput: Consider Input: Returning from a Hong Kong business trip, Beth Emhoff (Gwyneth Paltrow) has a layover in Chicago to rendezvous with a former lover before returning to her family in suburban Minneapolis. She appears to have contracted a cold during her trip. Her six-year-old son from a previous marriage, Clark, also becomes symptomatic and is sent home from school. Beth's condition worsens and two days later she collapses with severe seizures. Her husband, Mitch (Matt Damon), rushes her to the hospital, but she dies of an unknown cause.Mitch returns home and finds that Clark has also died from a similar infection. Mitch is put in isolation but seems to be immune to the disease. He is released and returns home to his teenaged daughter Jory, who had been living with Mitch's former wife and her husband and has decided to stay with Mitch since he's now all alone. They face decaying social order and rampant looting of stores and homes. Mitch is unsure if Jory has inherited his immunity and he struggles with the frustration of quarantine, his desire to protect his daughter and learning that his wife was cheating on him immediately prior to both her death and that of his stepson.In Atlanta, representatives of the Department of Homeland Security meet with Dr. Ellis Cheever (Laurence Fishburne) of the CDC and express fears that the disease is a bio weapon intended to cause terror over the Thanksgiving weekend. Dr. Cheever dispatches Dr. Erin Mears (Kate Winslet), an Epidemic Intelligence Service officer, to Minneapolis to begin investigating. Mears traces the outbreak back to Emhoff while negotiating with local bureaucrats initially reluctant to commit resources for a proper public health response to the virus. Dr. Mears later becomes infected and dies.At the CDC, Dr. Ally Hextall (Jennifer Ehle) determines the virus is a mix of genetic material from pig and bat viruses. Work on a cure stalls because scientists cannot discover a cell culture within which to grow the newly identified Meningoencephalitis Virus One (MEV-1).UCSF professor Dr. Ian Sussman (Elliott Gould) violates orders from Cheever (relayed through Hextall) to destroy his samples, and identifies a usable MEV-1 cell culture using bat cells. Hextall uses the breakthrough to work on a vaccine. Other scientists determine the virus is spread by fomites, with a basic reproduction number of four when the virus mutates, with projections of one in twelve of the population being infected, and a 25-30% mortality rate.Conspiracy theorist Alan Krumwiede (Jude Law) posts videos about the virus on his popular blog. In one video, he shows himself sick and later claims he recovered using a homeopathic cure derived from forsythia. In a panic, people seeking forsythia overwhelm pharmacies, spreading and accelerating the contagion as the infected come into contact with healthy people.Krumwiede's claims attract national attention. During a television interview he discloses that Dr. Cheever had secretly informed friends and family to leave Chicago just before the city was quarantined. Cheever is then informed the government will investigate and may charge him for leaking information. Later it is revealed Krumwiede had faked being infected by the virus in an attempt to increase profits for shareholders in companies producing and selling forsythia. Krumwiede is arrested for conspiracy and securities fraud, only to walk free when his many supporters successfully raise funds to provide for his bail.Using an attenuated virus Dr. Hextall identifies a possible vaccine. To cut out the lengthy time it would take to obtain informed consent from infected patients, Dr. Hextall inoculates herself with the experimental vaccine and immediately visits her gravely ill father, who has been infected with MEV-1. The doctor does not contract MEV-1 and the vaccine is declared a success.The vaccine's production is rapidly increased, but due to limited production, the CDC awards vaccinations by lottery based on birth date. Inoculations take place for one full year until every survivor is vaccinated. First responders, doctors and others designated by the government are declared exempt from the lottery. Dr. Cheever gives his fast-tracked MEV-1 vaccination to the son of Roger (John Hawkes), a CDC janitor who had overheard Dr. Cheever's phone call warning his girlfriend to leave Chicago.Dr. Leonora Orantes (Marion Cotillard), a WHO epidemiologist, travels to Hong Kong to follow the Beth Emhoff lead. She collaborates with Sun Feng (Chin Han) and other local epidemiologists and public health officials; they identify Emhoff as patient zero. As the virus spreads, Feng kidnaps Orantes to use her as leverage to obtain MEV-1 vaccine doses for his village. Orantes spends months living with the villagers until the vaccine is announced. Feng exchanges Orantes for the vaccine doses. Her colleague mentions that the exchanged doses were placebos and Orantes rushes away to warn them.The death toll reached 2.5 million in the U.S. and 26 million worldwide. Dr. Hextall places samples of MEV-1 in cryogenic storage, alongside samples of H1N1 and SARS.The source of the virus is revealed to viewers. A bulldozer (coincidently, operating for the company Emhoff works for) knocks down a palm tree disturbing some bats, with one finding shelter and food in a banana tree. That bat then flies over a pig pen, dropping a chunk of banana from its mouth, which is then eaten by a piglet. Chinese chefs later collect pigs from the pen and take them to a Hong Kong casino. A chef is called away from his preparations of a piglet, and casually wipes his hands on his apron. The chef then shakes hands with Beth Emhoff, giving her the mix of bat and pig viruses that makes her patient zero and the origin of the MEV-1 virus., Question: Who posts videos about the virus in his popular blog?\n\nOutput: Answer: Alan Krumwiede\n\n\nInput: Consider Input: Following the events of Ring, the body of Ryji Takayama, former husband of Reiko Asakawa and father of Yichi Asakawa, is examined by his friend and rival, pathologist Mitsuo And. After he finds a cryptic note in Takayama's stomach, Reiko and Yichi also turn up dead. And soon learns of a mysterious cursed videotape, haunted by the spirit of a murdered young woman. Rumor has it that anyone who watches the video will die exactly one week later. Despondent over the death of his own child, and believing that he is being guided by his rival's ghost, And decides to see the video for himself. After watching the tape, strange things begin to happen around him, and he soon discovers that the tape's restless spirit has different plans in store for him.With the help of Takayama's student, Mai Takano, And finds out more about Ryji's past as well as the mysterious young woman, Sadako Yamamura. Searching for the truth about why Ryji and Yichi died from the virus while Reiko didn't leads him to her boss Yoshino. Yoshino lets And in on a secret: he has the wife's diary. She and Ryji had been researching the cursed videotape. While Reiko had broken the curse, Ryji died a week after watching the tape. Reiko believed that creating a copy would break the curse but Yichi died a week after watching the tape, just as his father had. Yoshino shows And both the tape and the diary.When And tells Mai Takano what he's done, she is shocked and can't understand why, since she felt from the start that it was the video that killed Takayama and his family. As they are talking, Yoshino calls And. He admits that he wishes he'd never been involved in Reiko's business. And believes that Yoshino had watched the video, but he denies it saying that he was too scared to. However, Yoshino still dies.And decides to destroy the videotapes and make sure that he will be the video's last victim. He then confides in Mai about his son's death, and they end up sleeping together. And asks Mai if she'll be there with him when he dies, but Mai tells him she's too scared. He understands and decides to try to find out more about the virus that killed Takayama and his son. He discovers that the virus that killed Yoshino was different from the one that killed the father and son. And asks for tests to be run on him.Meanwhile, Mai Takano goes missing and And apparently survives the curse. He starts to feel that the story was just a myth and he's relieved when Mai turns up. However, he is shocked to find out that she has been found dead, having given birth with no sign of a baby. And goes back to work and sees \"Mai\" there. This woman claims to be Mai's sister but after a date and a night of intimacy, And finds out that she is none other than Sadako Yamamura, reborn and claiming to be \"perfectly dual-gendered\". He then learns that Takayama wasn't helping And stop Sadako instead, he and his family were helping her. Yoshino, Miyashita (And's friend) and many others weren't killed by a virus or the video but rather Ryji's wife's diary.In the end, And clones both Takayama and his son back to life with help from Sadako. Just as Ryji leaves, he tells And \"Many years will pass before our world will be at peace.\", Question: Who also died?\n\nOutput: Answer: Yoshino\n\n\nInput: Consider Input: In 1947 Portland, Maine, banker Andy Dufresne is convicted of murdering his wife and her lover, and is sentenced to two consecutive life sentences at the Shawshank State Penitentiary. Andy is befriended by contraband smuggler, Ellis \"Red\" Redding, an inmate serving a life sentence. Red procures a rock hammer and later a large poster of Rita Hayworth for Andy. Working in the prison laundry, Andy is regularly assaulted by \"the Sisters\" and their leader, Bogs.In 1949, Andy overhears the captain of the guards, Byron Hadley, complaining about being taxed on an inheritance, and offers to help him legally shelter the money. After an assault by the Sisters nearly kills Andy, Hadley beats Bogs severely enough that he never walks nor eats solid foods again, and is then transferred to a prison hospital. (And the Sisters never touch him again after that.) Warden Samuel Norton meets Andy and reassigns him to the prison library to assist elderly inmate Brooks Hatlen. Andy's new job is a pretext for him to begin managing financial matters for the prison employees. As time passes, the Warden begins using Andy to handle matters for a variety of people, including guards from other prisons and the warden himself. Andy begins writing weekly letters asking the state government for funds to improve the decaying library.In 1954, Brooks is paroled, but cannot adjust to the outside world after fifty years in prison, and commits suicide by hanging himself. Andy receives a library donation that includes a recording of The Marriage of Figaro. He plays an excerpt over the public address system, resulting in him receiving solitary confinement. After his release from solitary, Andy explains that hope is what gets him through his time, a concept that Red dismisses. In 1963, Norton begins exploiting prison labor for public works, profiting by undercutting skilled labor costs and receiving bribes. He has Andy launder the money using the alias Randall Stephens.In 1965, Tommy Williams is incarcerated for burglary. He is befriended by Andy and Red, and Andy helps him pass his GED exam. In 1966, Tommy reveals to Red and Andy that an inmate at another prison claimed responsibility for the murders for which Andy was convicted. Andy approaches Norton with this information, but he refuses to listen and sends Andy back to solitary confinement when he mentions the money laundering. Norton has Hadley murder Tommy under the guise of an escape attempt. Andy declines to continue the laundering, but relents after Norton threatens to burn the library, remove Andy's protection from the guards, and move him to worse conditions. Andy is released from solitary confinement after two months, and tells Red of his dream of living in Zihuatanejo, a Mexican coastal town. Red feels Andy is being unrealistic, but promises Andy that if he is ever released, he will visit a specific hayfield near Buxton, Maine, and retrieve a package Andy buried there. He worries about Andy's well-being, especially when he learns Andy asked another inmate to supply him with six feet (1.8 meters) of rope.The next day at roll call, the guards find Andy's cell empty. An irate Norton throws a rock at the poster of Raquel Welch hanging on the cell wall, revealing a tunnel that Andy dug with his rock hammer over the last 19 years. The previous night, Andy escaped through the tunnel and prison sewage pipe, using the rope to bring with him Norton's suit, shoes, and the ledger containing details of the money laundering. While guards search for him, Andy poses as Randall Stephens and visits several banks to withdraw the laundered money, then mails the ledger and evidence of the corruption and murders at Shawshank to a local newspaper. FBI agents arrive at Shawshank and take Hadley into custody, while Norton commits suicide by shooting himself to avoid his arrest.After serving forty years, Red is finally paroled. He struggles to adapt to life outside prison and fears he never will. Remembering his promise to Andy, he visits Buxton and finds a cache containing money and a letter asking him to come to Zihuatanejo. Red violates his parole and travels to Fort Hancock, Texas to cross the border to Mexico, admitting he finally feels hope. On a beach in Zihuatanejo he finds Andy, and the two friends are happily reunited., Question: What alias did Andy use to launder money?\n\n"
},
{
"from": "gpt",
"value": "Output: Answer: Randall Stephens\n\n\n"
}
] |
[
{
"from": "human",
"value": "Q: The input is a tweet which can be classified as Hate Speech, Offensive or Normal. Given such a tweet, output the class the tweet belongs to. Hate Speech will contain threatening language towards the community targeted. Offensive language will contain abusive or discriminatory language towards the community targeted.\nwhy do so many feminists have that retarded fish face feminism\nA:"
},
{
"from": "gpt",
"value": "Offensive"
}
] |
[
{
"from": "human",
"value": "In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative\n\nEx Input:\nA disoriented but occasionally disarming saga packed with moments out of an Alice in Wonderland adventure , a stalker thriller , and a condensed season of TV 's Big Brother .\n\nEx Output:\nPOS\n\n\nEx Input:\nBoth exuberantly romantic and serenely melancholy , What Time Is It There ?\n\nEx Output:\nPOS\n\n\nEx Input:\nIt 's dark and tragic , and lets the business of the greedy talent agents get in the way of saying something meaningful about facing death\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "POS\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a question. You have to answer the question based on your information.\nQ: What is the weekly feminist letter is Jessica Grose editor in chief of?\nA:"
},
{
"from": "gpt",
"value": "Lenny Letter"
}
] |
[
{
"from": "human",
"value": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\nOne example is below.\nQ: Passage: Omelettes make a great breakfast , and I enjoy making them because they are very easy to cook . First , I get the eggs out and begin cracking them on the side of the bowl and dumping them into the bowl . I normally use two eggs whites and one whole egg to cut the calories . I add some salt and pepper to the mix for flavor . I pour the mixture into the hot frying pan . I make sure that I add some vegetable oil to the pan before I add the eggs though because I do n't want them to stick . As this occurs , I add some cheese or vegetable to the center of the egg mixture . Really , almost any type of cheese or vegetable makes a good omelette . I then flip one side of the omelette over on to itself to seal in the contents in the middle . It is then ready to serve ! Question: Where is the omelette being browned? Option1: In the pan Option2: On the street\nA: In the pan\nRationale: As mentioned in the passage that I pour the mixture into the hot frying pan; it is clear that omelette is being browned in pan only. Also, there is nothing related to street mention in the passage.\nQ: Passage: On Saturday morning , we arrived at the church about 15 minutes before the wedding ceremony was supposed to start . I saw some friends and said hi , even though the organist was playing and we were standing very close to her and it was hard to hear each other . When we took our seats , my wife said , \" I think the organist is doing a great job ! She is playing beautifully ! \" and I nodded in agreement . Almost immediately after , then song dramatically changed to a new song , signaling that the ceremony was about to start . The wedding party started down the aisle , and when they were all lined up at the altar , there was another dramatic change in the organ music . She walked the aisle , accompanied by the organ music , which was lovely , until she reached the altar and the vows began . Question: When did the bride appear at the doors? Option1: After the change in music Option2: After wedding\nA:"
},
{
"from": "gpt",
"value": "After the change in music"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a part of privacy policy text, identify the purpose for which the user information is collected/used. The purpose should be given inside the policy text, answer as 'Not Specified' otherwise\nSee one example below:\nProblem: The site collects your IP address or device IDs for advertising. Collection happens when you implicitly provide information on the website.\nSolution: Advertising\nExplanation: The given policy text states that it uses user information for 'advertising' explicitly\n\nProblem: You can use privacy configuration settings (in the website or app) to control the use of activities on the website or app by the site, which uses it for advertising.\nSolution:"
},
{
"from": "gpt",
"value": "Advertising"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a four sentences of story written in natural language. Your job is to complete end part of the story by predicting appropriate last sentence which is coherent with the given sentences.\n\nLet me give you an example: Sentence1: 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.\nThe answer to this example can be: He is happy now.\nHere is why: As mentioned in last sentence, the incident turned a new leaf to Rick's life; this part completes the story properly.\n\nOK. solve this:\nSentence1: At the fair, Jason entered the ugliest cake contest. Sentence2: He decorated his cake green with green gummy worms. Sentence3: He called his cake the Mean Green Worm Machine. Sentence4: Nancy, from a spice company, looked over the cakes.\nAnswer:"
},
{
"from": "gpt",
"value": "Jason won first place."
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn 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.\nPart 2. Example\nText: quick backstory: i am a duel enrollment student (still in high school but goes to college full-time) and don't have my license so i bike home. \n\nnow let's get to the fuck up. i was riding down the sidewalk and up ahead was a golf cart blocking the way. the man who was using kindly moved it out of my so i could get past. as i go by, i give him the nod and say \"thank you\" just to be courteous. well he didn't really give me that much space so as i was saying thank you, my goes into the grass and i quickly try to readjust, resulting in my tire hitting the side of the sidewalk and me falling off my bike. i looked like a complete dumbass and just laughed to myself and kept riding. luckily, i don't take myself too seriously, so i wasn't that embarrassed.\nAnswer: said thank you, fell off my bike.\nExplanation: This summary is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"thanking someone and later falling off from the bike\".\nPart 3. Exercise\nText: so, im sitting here at work waiting for my wife to come pick me up for lunch, i message her and tell her to text me when she gets here because fb is messing up and im not getting all of my messages on there. so sitting here... the owner of the company i work for is standing by the doors talking to her daughter, this is an older little lady. they tell me my wife has pulled up into the parking lot so i get up put on my coat as im just as i am approaching the front doors where they are chatting i feel my phone start vibrating and in like slow motion i hear \"english motherfucker do you speak it\" full volume ringer , i slam my hand on my phone half way through the tone trying to muffle it but i don't think it worked i sprinted out the door. i hope she didn't hear it lol. i then went and had some pizza hut buffet mmm.\nAnswer:"
},
{
"from": "gpt",
"value": "i blared some inappropriate stuff out of my phone in front of a little old lady, then had pizza."
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context, a question, and three options. Your task is to find the correct answer to the question using the given context and options. Also, you may need to use commonsense reasoning about social situations to answer the questions. Classify your answers into 'A', 'B', and 'C'.\n\nQ: Context: Alex had a fun party at his house with his friends and people he knew. \n Question: How would Others feel as a result? \n Options: (A) social (B) nervous (C) anxious\n\nA: A\n****\nQ: Context: Remy lit every candle when the power went out. \n Question: What will Remy want to do next? \n Options: (A) find all the candles (B) get a flashlight (C) throw the matches out\n\nA: B\n****\nQ: Context: Taylor raised up Cameron's arms because they were reenacting a scene from the Bible. \n Question: Why did Taylor do this? \n Options: (A) question taylor (B) tell a story (C) be wrong\n\nA:"
},
{
"from": "gpt",
"value": "B\n****\n"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.