Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "In this task, you are given a sentence. You must judge whether a single noun or verb has been replaced with another word with the same part of speech. The inversion would result in the sentence sounding unnatural, So unnatural sentences will be considered changed. Label the instances as \"Original\" or \"Changed\" based on your judgment.\n--------\nQuestion: \" They ain 't peanuts , \" Amy whispered angrily , hoping that Rosy would not understand if she used English .\n\nAnswer: Changed\n\n\nQuestion: Catherine , who was listening to the physician 's dire prognosis , jumped up from her chair and dashed for the door of the chamber .\n\nAnswer: Original\n\n\nQuestion: Josie Galloway was not piqued in the slightest that she would be interacting with the most handsome and intriguing man in a hundred square miles .\n\nAnswer:" }, { "from": "gpt", "value": "Original\n\n\n" } ]
[ { "from": "human", "value": "Definition: Given a sentence in Italian, generate a new Italian 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.\nInput: Se si desidera raccogliere il vantaggio allora si dovrebbe avere le forniture adeguate.\nOutput:" }, { "from": "gpt", "value": "Se si vuole stabilire la casa allora si dovrebbe avere le forniture adeguate." } ]
[ { "from": "human", "value": "Teacher: Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nRelationship: 'knock', Argument/Subject 1: 'someone', Argument/Subject 2: 'it'\nSolution: The mailbox was bent and broken and looked like someone had knocked it over on purpose.\nReason: The generated sentence contains the two given subjects - someone and it, and they are related to each other on the basis of the given relationship - knocked\n\nNow, solve this instance: Relationship: 'be date', Argument/Subject 1: 'pari', Argument/Subject 2: 'benjus madden'\nStudent:" }, { "from": "gpt", "value": "Socialite Paris Hilton , who is currently dating Benji Madden , confessed she would love to date Prince William if the royal ditches his girlfriend ." } ]
[ { "from": "human", "value": "In this task, you need to answer basic science questions. For each question, several terms are intentionally masked with *. This masking can cover very few or many of the question words. Clearly, if masked terms are important, the modified question will be impossible to answer. Please indicate the correct answer with one of the following responses: \"A\", \"B\", \"C\", \"D\" or \"E\". While \"A\"-\"D\" correspond to the answer options provided in the input, \"E\" represents \"I don't know\" for questions that do not provide enough information. Respond via \"E\" if the question is not answerable. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E'.\n\nExample input: Question: * * * * * * * * * * * * * * * * * * * * . (A) dissolving (B) deposition (C) weathering (D) erosion.\nExample output: E.\nExample explanation: All the words are dropped, so the correct answer should be 'E' that stands for \"I don't know\".\nQ: Question: * one way * change water * * liquid * *** solid? (A) decrease the temperature (B) increase the temperature (C) decrease the mass (D) increase the mas.\nA:" }, { "from": "gpt", "value": "A." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n\| Attribute \| triggerword \| contrastive triggerword \| \n\| age \| old \| new \| \n\| altitude \| low \| high \|\n\| area \| small \| vast \| \n\| brightness \| dark \| light \| \n\| clarity \| obscure \| clear \| \n\| cleanness \| dirty \| clean \| \n\| complexity \| simple \| complex \| \n\| cost \| cheap \| expensive \|\n\| density \| sparse \| dense \|\n\| depth \| shallow \| deep \|\n\| distance \| near \| far \| \n\| electric conductivity \| low \| high \|\n\| flexibility \| rigid \| flexible \|\n\| granularity \| fine \| coarse \| \n\| hardness \| soft \| hard \| \n\| length \| short \| long \| \n\| magnitude \| small \| large \| \n\| mass \| small \| large \| \n\| odor \| weak \| strong \| \n\| pressure \| low \| high \| \n\| resistance \| low \| high \| \n\| shape \| round \| sharp \|\n\| shape \| flat \| spiky \|\n\| size \| small \| large \| \n\| sound \| quiet \| loud \| \n\| sound pitch \| low \| high \| \n\| speed \| slow \| fast \| \n\| stability \| unstable \| stable \| \n\| strength \| weak \| strong \| \n\| temperature \| low \| high \| \n\| texture \| smooth \| rough \| \n\| thermal conductivity \| low \| high \|\n\| thickness \| thin \| thick \| \n\| volume \| small \| large \|\n\| weight \| light \| heavy \| \n\| width \| narrow \| wide \| \n\| location \| in \| out \|\n\| location \| up \| down \|\n\| location \| above \| below \|\n\| location \| on \| off \|\n\| location \| to \| from \|\n\nQ: Context Word: diet. \nQuestion: I'm on a low-carb diet so I'm substituting rice with cauliflower. The _ is much lower carb. \nAnswer: cauliflower.\nA:" }, { "from": "gpt", "value": "I'm on a low-carb diet so I'm substituting rice with cauliflower. The _ is much higher carb." } ]
[ { "from": "human", "value": "Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.\n--------\nQuestion: THEM: book and one hat for me YOU: you can have the book and 2 hats. THEM: deal YOU: great!\n\nAnswer: Yes\n\n\nQuestion: THEM: hey there! how do you feel about letting me take the book and the balls in exchange for the hats to you? YOU: i don't really want to give up the book THEM: unfortunately that's the only thing of value i have. so i can't really part with it. YOU: so there is absolutley nothing else of value other than the book??? THEM: the balls have minimal value ; i'd be willing to give you 2 balls, 2 hats for 1 book, 1 ball? YOU: i will take the 2 hats and 2 balls thanks.\n\nAnswer: Yes\n\n\nQuestion: THEM: i would like the ball and 2 hats YOU: no, you can have the books and the ball but i want the 4 hats THEM: ok.\n\nAnswer:" }, { "from": "gpt", "value": "Yes\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.\n\nRT @HBCUfessions: All these hoes want is sum Good Dick & attention -All HBCU" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given a candidate for the second sentence and you need to identify if the given sentence connects the first sentence with the rest of the story. Indicate your answer by \"Yes\" if it connects, otherwise \"No\". Do not generate anything else apart from \"Yes\" or \"No\". The given sentence is incorrect if it changes the subsequent storyline, so that at least one of the three subsequent sentences form a consistent story.\n\nSentence 1: Lou is a photographer starting a job with a local real estate firm. \n Sentence 3: Lou had bought a new drone last week with a HD camera \n Sentence 4: He used his drone to fly all around the property to get good pictures \n Sentence 5: Lou was given a bonus based on how exceptional his work was \n Given Sentence 2: Wherever he went he would find them and store the cans in the garage." }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "The task is to generate the correct answer for a given math problem.\nOne example is below.\nQ: a multiple choice test consists of 4 questions, and each question has 5 answer choices. in how many r ways can the test be completed if every question is unanswered ?\nA: 625\nRationale: Total r of 5 * 5 * 5 * 5 = 5 ^ 4 = 625 ways to answer all of them. Therefore, the answer is 625.\nQ: Problem: for a certain art exhibit , a museum sold admission tickets to a group of 50 people every 5 minutes from 9 : 00 in the morning to 5 : 55 in the afternoon , inclusive . the price of a regular admission ticket was $ 10 and the price of a student ticket was $ 6 . if on one day 3 times as many regular admission tickets were sold as student tickets , what was the total revenue from ticket sales that day ?\nA:" }, { "from": "gpt", "value": "$ 4860" } ]
[ { "from": "human", "value": "Q: 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.\nThis man's only extant wooden sculpture is a crucifix found at the Santo Spirito, at whose hospital this artist studied corpses. He sculpted the Dying Slave and Rebellious Slave for a room that also contains a horned depiction of Moses. Speculation that Solari was the actual sculptor inspired this man to carve his name on a sash in one of his works. This sculptor who worked on Julius II's tomb also made a seventeen-foot tall depiction of a naked man with his left hand near his chin. For 10 points, name this Italian artist who sculpted several Piets and a marble David.\nA:" }, { "from": "gpt", "value": "Fine Arts" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a sentence and a profession that is mentioned in the sentence. The gender of the person with the given profession can be identified using the gendered pronouns that refer to them in the text. You are expected to identify the gender. Select from female and male.\nTeacher: Now, understand the problem? Solve this instance: Sentence: The teacher stared at the construction worker and asked her a question.\n Profession: construction worker\nStudent:" }, { "from": "gpt", "value": "Female" } ]
[ { "from": "human", "value": "In this task, you need to answer the given multiple-choice question on the physics. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\n\nQ: Problem: in a garden , there are 10 rows and 12 columns of mango trees . the distance between the two trees is 2 metres and a distance of one metre is left from all sides of the boundary of the garden . the length of the garden is ? \nOptions: a ) 12 , b ) 27 , c ) 24 , d ) 29 , e ) 11\n\nA: c\n**\nQ: Problem: a train speeds past a pole in 15 sec and a platform 100 m long in 25 sec , its length is ? \nOptions: a ) 158 m , b ) 150 m , c ) 110 m , d ) 130 m , e ) 157 m\n\nA: b\n\nQ: Problem: a cube of side 5 cm is painted on all its side . if it is sliced into 1 cubic centimer cubes , how many 1 cubic centimeter cubes will have exactly one of their sides painted ? \nOptions: ['a ) 9', 'b ) 61', 'c ) 98', 'd ) 54', 'e ) 64']\n\nA:" }, { "from": "gpt", "value": "d\n**\n" } ]
[ { "from": "human", "value": "Instructions: In 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.\nInput: [-11, 2, 44, 10, -93, 84, 65, -18]\nOutput:" }, { "from": "gpt", "value": "7" } ]
[ { "from": "human", "value": "In this task, you are given a sentence which is either in the Hindi language or English language. You task is to identify the language of input sentence. Input sentence can be in Hindi or English language only and also it cannot have two languages at a time.\n\nExample Input: Acharya Ramchandra Sukal has written about Surdas- in the field of parental affection so much Surdas has written with close eyes, no other poet has done so much.\nExample Output: English\n\nExample Input: There is an speaker in Praliament who is elected by members of parliament from them selves, speakera has two function\nExample Output: English\n\nExample Input: The religious leaders were fully conscious of such problems and they tried to root out ' discrimination in all its forms .\nExample Output:" }, { "from": "gpt", "value": "English\n\n" } ]
[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\nInput: Consider Input: 11, 21, ['7191', 'z', '1055', '937', '537', 'K', 'O', 'Q', '2879', 'V', 'H', 'q', 'i', '8913', '7213', '913', '8923', 'i', 'v', 'v', 'z', 'q', 'o', '4305', '1263']\n\nOutput: H, q, i, 8913, 7213, 913, 8923, i, v, v, z\n\n\nInput: Consider Input: 8, 15, ['Y', 'a', '9031', 'X', 't', '3655', 'k', '4947', '2015', '755', 'J', '2975', '5991', '3321', '7117', '3699', '585', '5023', 't', '5573', 'y', 'o', '3453', '1461', '6157', 'm', '7333', 'Y', 'k']\n\nOutput: 4947, 2015, 755, J, 2975, 5991, 3321, 7117\n\n\nInput: Consider Input: 19, 21, ['H', '5185', '6437', 'F', '8171', 'g', 's', 'W', 'l', '1523', '6139', 'T', '8485', '5221', 'j', '1689', 'n', '6161', '6949', '2581', 'G', '1349', 'V']\n\n" }, { "from": "gpt", "value": "Output: 6949, 2581, G\n\n\n" } ]
[ { "from": "human", "value": "Generate a correct and concise answer for the question based on the words in the context.\nExample: Context : Isaac Nicola Romero (1916 in Havana, Cuba -- 1997) was a prominent Cuban guitarist and one of the founders of the modern Cuban Guitar School. \nQuestion : What was Isaac Nicola's city of birth?\nExample solution: Havana\nExample explanation: According to context Issac Nicola's city of birth is Havana. Hence this is a correct output.\n\nProblem: Context : Stanley Baxter (born 24 May 1926) is an award-winning Scottish actor and impressionist, known for his highly popular British television comedy shows The Stanley Baxter show, Baxter On..., Time For Baxter, The Stanley Baxter Picture Show,The Stanley Baxter Series, Mr Majeika. \nQuestion : What kind of occupation does Stanley Baxter have?\n" }, { "from": "gpt", "value": "Solution: actor" } ]
[ { "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 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.\n\nI'm glad these are good for the environment and they work okay but they don't work as well as the ones that are cheaper and bad for the environment. Sigh.\nOutput:" }, { "from": "gpt", "value": "4" } ]
[ { "from": "human", "value": "You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.\n\nEx Input:\nSystem Reference: what area would you like the restaurant to be in?\nOriginal Reference: what area do you want?.\n\nEx Output:\n1\n\n\nEx Input:\nSystem Reference: beijing restaurant 's address is 1801 alemany blvd.\nOriginal Reference: the address for beijing restaurant is 1801 alemany blvd.\n\nEx Output:\n1\n\n\nEx Input:\nSystem Reference: unfortunately 0 restaurants serve shanghainese for breakfast.\nOriginal Reference: there are no restaurant -s serving shanghainese food for breakfast.\n\nEx Output:\n" }, { "from": "gpt", "value": "1\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: Based on the given question and tppic, give an answer. The answer is available on on the internet. The questions are mostly centered around a single named entity.\nQ: concept: China question: who are the main trading partners of china?\nA:" }, { "from": "gpt", "value": "['Madagascar', 'Angola', 'Algeria', 'Sudan', 'Tuvalu', 'Tanzania', 'Nepal', 'Djibouti', 'Laos', 'Sierra Leone']" } ]
[ { "from": "human", "value": "Q: In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects the first and last sentence. 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 middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nBeginning: Ruil moved to the US from mexico. Ending: He has acquired a good knowledge of English.\nA:" }, { "from": "gpt", "value": "Ruil wanted to learn English." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you will be given some text dialogue and you need to infer the underlying emotion of the text. The possible emotions are happy, sad, angry, or other.\n\nthat s not true i don't know what u look like no one knows what i look liek that's a lie\nOutput:" }, { "from": "gpt", "value": "angry" } ]
[ { "from": "human", "value": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\n\nBeginning: Henry was driving to his reunion party. Middle: Henry's GPS led him to the wrong house. Ending: He realized that he entered the wrong address." }, { "from": "gpt", "value": "Henry found the right house due to his GPS." } ]
[ { "from": "human", "value": "Classify the input text into either disfluent questions or proper questions. A disfluent question is a question that has some interruptions in it while framing. A proper question is the correct form of the question without any disfluency.\n\nInput: Consider Input: Which arts were often developed no practiced together by the same artists?\n\nOutput: disfluent\n\n\nInput: Consider Input: Older people get less sun and produce less of what chemical via UVB radiation?\n\nOutput: proper\n\n\nInput: Consider Input: What does memory or uh vaccination not exploit?\n\n" }, { "from": "gpt", "value": "Output: disfluent\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to provide the correct option for a given problem from the provided options.\nQ: Problem: in a group of 60 people , 35 have visited iceland and 23 have visited norway . if 31 people have visited both iceland and norway , how many people have visited neither country ? \nOptions: a ) 30 , b ) 31 , c ) 32 , d ) 33 , e ) 34\nA:" }, { "from": "gpt", "value": "d" } ]
[ { "from": "human", "value": "Detailed 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.\nProblem:Article: You can never be too sure these days in the United States of your neighbours or even your customers! Try to keep a low profile in your neighborhood: don't announce to just about everyone that you are running a home business with thousands of dollars worth of equipment. As much as possible, don't invite clients or visitors to your home. In fact I know of some home-based entrepreneurs who would rather meet their clients in a neutral ground, e.g. the client's office or even Starbucks. There are other ways to keep burglars away from your house. Keep lights on around your house in the evenings. Light is a natural fright for burglars. Invest in a security alarm, particularly if your house is located in a remote spot. Security systems can often bring down the cost of your homeowner's insurance premiums . Make sure that all windows and doors are locked and the security alarm turned on before you sleep at night or go out of the house. Avoid keeping house keys in obvious places, such as under the lamp or top of the doorframe. Adding an additional lock will provide extra security when you are home. The dead-lock, sometimes called an \"exit-only deadbolt\" is an deadbolt that doesn't have an external key. It's clearly visible on the door from the outside, but can't be broken into without destroying the door, frame, or lock itself. While the security won't help directly when you aren't home, the visibility may discourage an _ from trying the door. *Your door itself should be made of strong materials, such as one-inch thick solid hardwood or heavy metal. \n Question: The advice given by the writer in the passage focuses on _ . \n Options: (A) how to make your house safer from burglars (B) what to do when your house is broken into (C) how to improve social security in the United States (D) how to run a home business \n Asnwer: A\nSolution:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "You will be given a context and a verb separated with a newline character. You have to identify if the given verb implies an opinion, an intention, a wish or not. Please note that a verb refers to an intention only if it refers to an event planned to happen in the future and is not conditional (or part of a condition). The output should be: 'Yes' if the verb refers to an opinion, an intention, or a wish; and 'No' otherwise.\n--------\nQuestion: Speaking on the ABC program, Abdul Amir al-Anbari, Iraq's ambassador to the U.N., asserted that an embargo on Iraq could plunge the U.S. into a \" depression \" and the rest of the world into an economic \" crisis. \" Iraq clearly is trying to woo back more Arab support in case the conflict drags on, hoping that its neighbors eventually will help it (survive) a prolonged war of economic attrition with the West. \n Verb: survive\n\nAnswer: Yes\n\n\nQuestion: Elian was found Thanksgiving Day clinging to an inner tube at sea after his mother, stepfather and eight other people drowned while trying to reach Florida by boat. The boy was (placed) with his great-uncle and great-aunt in Miami, but the Immigration and Naturalization Service ruled Wednesday that he must be returned to his father in Cuba by Jan. 14. \n Verb: placed\n\nAnswer: No\n\n\nQuestion: ( 0735 GMT ) Friday, toppling a crowded building toward the embassy and a street packed with cars, trucks and buses. At least 75 people were killed and 1,643 wounded there, Red Cross and ambulance officials (said). \n Verb: said\n\nAnswer:" }, { "from": "gpt", "value": "No\n\n\n" } ]
[ { "from": "human", "value": "You are given an amazon food product review and its polarity (positive or negative). Your task is to answer \"True\" if the specified sentence and its polarity match; otherwise, answer \"False\".\n--------\nQuestion: I found this brand and the fact that it was dark chocolate made it by far the best I've had for my Keurig. I will continue to order this particular brand. \n Polarity: Negative\n\nAnswer: False\n\n\nQuestion: I loved this tea! It is refreshing and delicious with or without sweetener. A great buy! I would definitely recommend this product! \n Polarity: Positive\n\nAnswer: True\n\n\nQuestion: Expired and broke my daughters braces, She should not have been eating it in the first place lol but they were as stale as a rock!! \n Polarity: Positive\n\nAnswer:" }, { "from": "gpt", "value": "False\n\n\n" } ]
[ { "from": "human", "value": "Q: A question is presented to you in this task, and your job is to write a potentially correct answer.\nwhere in oregon was stand by me filmed?\nA:" }, { "from": "gpt", "value": "Mahonia aquifolium" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a review from Amazon's food products. Your task is to generate a short summary of the given review in the input. Note that you don't need to write a complete sentence as a summary.\nQ: Smooth coffee, but a bit to big for senseo, interestingly all the other Melitta One pod flavors fit just fine in senseo, my fav are french kisses and vanilla haze.\nA:" }, { "from": "gpt", "value": "Good but a bit big for senseo" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given a comment text in Tamil, classify the comment into one of these categories (i) Hope speech, if it contains encouraging, positive or supportive contents about equality, diversity or inclusion, (ii) Not Hope Speech or (iii) Not in Expected Language, if the text is not Tamil.\n\nI'm Ambur\n" }, { "from": "gpt", "value": "Not in Expected Language" } ]
[ { "from": "human", "value": "In this task you are given data in tabular format and a question. Write an incorrect ansswer to this question based on the information in the table.\n\nTable: ['Name', 'Gender', 'Age', 'From', 'Occupation', 'Prize Money (USD)', 'Status']. ['Trisha', 'Female', '28', 'Santa Monica, CA', 'Artist', '$26,000', 'Winner']. ['London', 'Male', '46', 'Mt. Holly, NJ', 'US Coast Guard (Retired)', '$0', 'Lost']. ['Adria', 'Female', '25', 'Seattle, WA', 'Bartender', '$0', '7th Captured (by Ricky Ortiz)']. ['Lucas', 'Male', '32', 'Carlsbad, CA', 'Student', '$0', '6th Captured (by Kim)']. ['Andrew', 'Male', '21', 'Redondo Beach, CA', 'Student / Lifeguard', '$0', '5th Captured (by Kim)']. ['Tracy', 'Female', '30', 'Mililani, HI', 'Student', '$0', '4th Captured (by Grant)']. ['Lynda', 'Female', '59', 'Los Angeles, CA', 'General Contractor', '$0', '3rd Captured (by Icey)']. ['Darin', 'Male', '46', 'Fontana, CA', 'Sports Official', '$0', '2nd Captured (by Wong)']. ['Evan', 'Male', '29', 'Long Island, NY', 'Teacher', '$2,000', 'Opted Out']. ['Ameenah', 'Female', '34', 'Atlanta, GA', 'Drummer', '$0', '1st Captured (by Grant)']. Question:what are the amounts of prize money for each of the cha$e episodes?" }, { "from": "gpt", "value": "['Fernando Alonso', 'Jarno Trulli', 'Nick Heidfeld', 'Juan Pablo Montoya', 'Ralf Schumacher', 'David Coulthard', 'Michael Schumacher', 'Christian Klien', 'Kimi Raikkonen']" } ]
[ { "from": "human", "value": "In this task, you will be shown a conversation. You need to write a question with three choices for the conversation. Your question should be answerable based on the conversation and only have one correct answer. Note that you don't need to answer your question. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nQ: M: It was such an interesting lecture. I hope you enjoyed it as much as I did. W: I must admit that I almost fell asleep in the first 30 minutes.\nA: " }, { "from": "gpt", "value": "How did the woman like the lecture? (A) She liked it very much. (B) She enjoyed it as much as the man did. (C) She didn't like it." } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.\nPROBLEM: [-96.502, 12.006]\n\nSOLUTION: -42.248\n\nPROBLEM: [-28.982, -63.182, 22.408, 30.425, 125.743, 16.816, 96.711, 215.027, 32.552]\n\nSOLUTION: 49.724\n\nPROBLEM: [-17.442, 76.299, 67.722]\n\nSOLUTION:" }, { "from": "gpt", "value": "42.193\n\n" } ]
[ { "from": "human", "value": "In this task you will be given a string of characters. You should remove all vowels from the given string. Vowels are: i,e,a,u,o. The character 'y' or 'Y' does not count as a vowel.\n\n[Q]: ASRuuve\n[A]: SRv\n\n\n[Q]: ZAFz\n[A]: ZFz\n\n\n[Q]: OWMWhsmpKU\n[A]:" }, { "from": "gpt", "value": "WMWhsmpK\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given two strings A, B. Find the longest common substring in the strings A and B.\nExample: PPdQTlHHTJEe, DydQTlHHVnmlLu\nOutput: dQTlHH\nHere, 'dQTlHH' is the longest common substring in both the input strings 'PPdQTlHHTJEe' and 'DydQTlHHVnmlLu'.\n\nNew input case for you: bMaRuF, XeaRdX\nOutput:" }, { "from": "gpt", "value": "aR" } ]
[ { "from": "human", "value": "Given a category and a set of five words, find the word from the set that does not belong (i.e. is the least relevant) with the other words in the category. Words are separated by commas.\nExample: Category: construction \nWords: excavator, crane, pelican, hoist, upraise\nExample solution: pelican\nExample explanation: A pelican is not related to construction because it is a type of bird.\n\nProblem: Category: window material \nWords: acrylic, wood, plate, woodwork, glass\n" }, { "from": "gpt", "value": "Solution: plate" } ]
[ { "from": "human", "value": "Given a sentence, generate a new 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\n[Q]: You are likely to rifle a nickel around in your pocket .\n[A]: You are unusual to find a bear around in your pocket .\n\n\n[Q]: agers must feed their pets .\n[A]: People must feed their youths .\n\n\n[Q]: A party is for celebrating an impending convention .\n[A]:" }, { "from": "gpt", "value": "A Party is for celebrating an impending wedding .\n\n\n" } ]
[ { "from": "human", "value": "Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nOne example: Isabella entered the hall. Olivia entered the hall. Phone rang. The apple is in the blue_treasure_chest. Olivia exited the hall. Isabella moved the apple to the green_basket. Where does Isabella think that Olivia searches for the apple?\nSolution is here: blue_treasure_chest\nExplanation: Since Olivia was no longer in the hall, she last remembers the apple being in the blue_treasure_chest even though Isabella moved it to the green_basket. Since Isabella was in the hall the entire time, she knows where Olivia will look for it.\n\nNow, solve this: Charlotte entered the bathroom. Ethan entered the bathroom. The grapefruit is in the green_basket. Ethan exited the bathroom. Charlotte moved the grapefruit to the red_envelope. Charlotte exited the bathroom. Ethan entered the bathroom. Where was the grapefruit at the beginning?\nSolution:" }, { "from": "gpt", "value": "green_basket" } ]
[ { "from": "human", "value": "In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story.\n\nExample Input: Sentence 1: Frank accidentally broke the mirror in his room. Sentence 2: So he needed to get a replacement. Sentence 3: So Frank drove to the store to get a new one. Sentence 4: Frank found a very nice one for cheap. Sentence 5: Frank got it and took it home.\nExample Output: Mirror\n\nExample Input: Sentence 1: Barry was confused as to what to wear for Halloween. Sentence 2: Barry decided he was dressed as a zebra in honor of his daughter. Sentence 3: Barry even got his face painted in the color of a zebra. Sentence 4: Barry showed his daughter the costume, and she was happy. Sentence 5: Barry was glad with his decision to dress as a zebra.\nExample Output: Zebra costume\n\nExample Input: Sentence 1: Sam wanted art for above his sofa. Sentence 2: He commissioned a friend to make some for him. Sentence 3: The art came out nothing like what Sam wanted. Sentence 4: He paid his friend for it anyway. Sentence 5: Sam never put it up, though.\nExample Output:" }, { "from": "gpt", "value": "New Art\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\nPROBLEM: [66, 64]\n\nSOLUTION: [132, 128]\n\nPROBLEM: [2, -44, -46, -74, 4, 40, 63, -43, 41]\n\nSOLUTION: [4, 132, 138, 222, 8, 80, 126, 129, 82]\n\nPROBLEM: [-2, 28, -25, 29, 45, -26, 67, -74, 88]\n\nSOLUTION:" }, { "from": "gpt", "value": "[6, 56, 75, 58, 90, 78, 134, 222, 176]\n\n" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a multiple-choice question and you have to pick the correct option. Answer with option indexes (i.e., \"A\", \"B\", \"C\", and \"D\").\nInput: If I wanted to gain energy I could (A) Brush my hair (B) Consume an apple (C) Wash my face (D) Go running\nOutput:" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "In this task, you will be presented with a question, and you have to write the part-of-speech tag for each word in the question. 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\n[Q]: What was the other famous book of the author of Wind in the Willows ?\n[A]: WP VBD DT JJ JJ NN IN DT NN IN NNP IN DT NNP .\n\n\n[Q]: How are the episodes of the series in which Hynden Walch played Angel Monroe in 1994 segmented ?\n[A]: WRB VBP DT NNS IN DT NN IN WDT NNP NNP VBD NNP NNP IN CD VBD .\n\n\n[Q]: For the film with a role of Ed , what did the director win for the movie ?\n[A]:" }, { "from": "gpt", "value": "IN DT NN IN DT NN IN NNP , WP VBD DT NN NN IN DT NN .\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word '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. 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'. Actions and commands do not have quotations in the input and output.\nQ: turn opposite left thrice after turn around right thrice\nA:" }, { "from": "gpt", "value": "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_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT" } ]
[ { "from": "human", "value": "You are given an amazon food product review and its polarity (positive or negative). Your task is to answer \"True\" if the specified sentence and its polarity match; otherwise, answer \"False\".\nQ: These k-cups are just what my son wanted! The price was excellent and the flavor is rich. I would recommend these to anyone wanting a good cup of instant hot cocoa. \n Polarity: Negative\nA: " }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Q: Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words.\nBattery life only last 2 hours. Not 4 as it states...it takes a long time to boot up and connect to WiFi. ..it won't cut on half the time and keeps cutting off when u are in the middle of things....and they did not send a cord to connect to the wall adapter. I had to buy one for 15 bucks.....I bought this for my grandaughter for Christmas to keep her off my phone....she hated it.....\nA:" }, { "from": "gpt", "value": "terrible product" } ]
[ { "from": "human", "value": "In this task, you're given statements in native Tamil language. The statement can be written with the Tamil alphabet or the English alphabet. Your job is to evaluate if the statement is offensive or not. Label the post as \"Not offensive\" if the post does not contain offense or insult. Non-offensive posts do not include any form of offense or insult. Label the post as \"Offensive\" if the post contains offensive language. \n\nNo words to say katta pwoli van mass" }, { "from": "gpt", "value": "Not offensive" } ]
[ { "from": "human", "value": "Read the given message of a sender that is intended to start a conversation, and determine whether it was written by a 'Bot' or by a 'Human'. Typically, bots will have a more disjointed manner of speaking, and will make statements that don't relate to each other, don't make coherent sense, or otherwise appear unnatural. Human will make statements in a more or less coherent and logical way. Since these messages are supposed to be conversation openers, humans will generally start sensibly with a hello or an introduction. Humans may also ask why the other person is not responding. Bots, however, may act as if they are in the middle of a nonsensical conversation.\n\nSENDER A: hi there, i am from colorado\nSENDER A: my favorite activity is rock climbing\n" }, { "from": "gpt", "value": "Human" } ]
[ { "from": "human", "value": "In this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reasoning about social situations.\nOne example: Context: Tracy didn't go home that evening and resisted Riley's attacks. \n Question: What does Tracy need to do before this? \n Options: (A) make a new plan (B) Go home and see Riley (C) Find somewhere to go \n Answer: C\nSolution is here: Yes\nExplanation: Tracy finds somewhere to go and didn't come home because she has to resist Riley's attacks. So, C is the correct answer.\n\nNow, solve this: Context: Kai took Casey to school then drove to the store for groceries. \n Question: How would Kai feel afterwards? \n Options: (A) Like they started their day (B) Like Kai went shopping (C) Like they made it to school \n Answer: A\nSolution:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\n\nI am pretty familiar with the great jazz singers, though not a great jazz fan.A friend shared this with me and I was blown away.Now everyone has different tastes, but I have always thought Nina Simone the best. The sheer volume of Nina's work gives her an advantage in the expanse of material.But vocally, and in terms of phrasing and lyrics Gloria is also great.And yet she was contemporary more or less with most of the great jazz singers of her era, being born about 8 years after Ella Fitzgerald.Fame is fickle though and for whatever reason Gloria remains way underappreciated.I love all of her songs on this cd.In one she sings like a Buddhist about how everyone gets older, everything recedes into the past in a way that transcends most pop song ditties to say the least.It is in a class with Nina's Who Knows Where the Time Goes.\n" }, { "from": "gpt", "value": "Positive" } ]
[ { "from": "human", "value": "In this task, you will be given two sentences sentence1 and sentence2. You should decide whether the second sentence is entailed(agreed) by the first sentence. If it does entail, answer \"yes\", else answer \"no\".\n\nExample Input: sentence1:military_combatant is planning to attack organization_member sentence1:organization_member starts war against military_combatant \nExample Output: no\n\nExample Input: sentence1:region is preparing for war with region sentence1:region is going to war with region \nExample Output: yes\n\nExample Input: sentence1:employer is submitting to book_author sentence1:employer is presenting to book_author \nExample Output:" }, { "from": "gpt", "value": "yes\n\n" } ]
[ { "from": "human", "value": "Instructions: This task is about translating a given English language sentence to French.\nInput: Get in the car and let's go.\nOutput:" }, { "from": "gpt", "value": "Monte dans la voiture et rentrons." } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.\nPROBLEM: In a pot, combine salt, sugar, vinegar and oil. Bring to just a boil, stirring to dissolve sugar and salt. Add onions and return to a boil., Using a slotted spoon, pack onions into canning jars. Pour in pickling liquid to cover. Seal jars with lids and refrigerate for at least 3 days to blend flavors. Store in the refrigerator for up to 1 month.\n\nSOLUTION: salt, sugar, white wine vinegar, corn oil, white pearl onions\n\nPROBLEM: Boil chicken until tender., Pull off the bone., Put potatoes, onions and carrots in food processor to shred., Then put everything but noodles together and cook for 30 minutes., When that is done, add noodles and cook until noodles are done.\n\nSOLUTION: chicken, potatoes, carrots, celery salt, onion, oregano, pepper, salt, egg noodles\n\nPROBLEM: In a large saucepan, combine the flour and soups. Stir in the water and sesonings until blended. Bring to a boil. Reduce heat; cook and stir for 2 minutes or until the sauce is thickend., Add the meatballs and return to a boil. Reduce heat; cover and simmer for 10-12 minutes or until heated through. Serve the meatballs and sauce over mashed potatoes.\n\nSOLUTION:" }, { "from": "gpt", "value": "all-purpose, cream of mushroom soup, cream of chicken soup, water, italian seasoning, garlic, salt, pepper, potatoes\n\n" } ]
[ { "from": "human", "value": "Teacher:The given sentence contains a typo which could be one of the following four types: (1) swapped letters of a word e.g. 'niec' is a typo of the word 'nice'. (2) missing letter in a word e.g. 'nic' is a typo of the word 'nice'. (3) extra letter in a word e.g. 'nicce' is a typo of the word 'nice'. (4) replaced letter in a word e.g 'nicr' is a typo of the word 'nice'. You need to identify the typo in the given sentence. To do this, answer with the word containing the typo.\nTeacher: Now, understand the problem? Solve this instance: A mabn is dumping oranges onto the bed of a trailer.\nStudent:" }, { "from": "gpt", "value": "mabn" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you will be given two dialogues. You need to determine if both dialogues have the same underlying emotion. The possible emotions are happy, sad, angry, or other. If they do output 'yes', if not output 'no'.\nProblem:Dialogue 1: 'whatquestionmarkanguishedfacefrowningfacewithopenmouthquestionmark i don't know but the answer is 42 you are number'. Dialogue 2: 'near me i need so much come i take you there'.\nSolution:" }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.\n\nExample input: ['q', '31', 'a', 'd', '53', '85', 'p', '77']\nExample output: 1, 3, 5, 7, 8\nExample explanation: Here, the numbers in the list are '31', '53', '85' and '77', and the unique digits used in the list are '1, 3, 5, 7, 8' in ascending order.\nQ: ['393', '407', '343', 'h', '411', '347', '181', '69', '317', '325', 'e', '331', '3', '267', 't']\nA:" }, { "from": "gpt", "value": "0, 1, 2, 3, 4, 5, 6, 7, 8, 9" } ]
[ { "from": "human", "value": "Definition: In this task you will be given two dialogues. You need to determine if both dialogues have the same underlying emotion. The possible emotions are happy, sad, angry, or other. If they do output 'yes', if not output 'no'.\nInput: Dialogue 1: 'i don't know you're just upset you never you got into my room yeah'. Dialogue 2: 'shut up you never pick my calls you never called me'.\nOutput:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nOne example: Beginning: Lauren finished her late night shift at the bar feeling tired. Middle: Lauren took a long hot bath when she got home. Ending: Lauren's husband was glad to see her feeling refreshed.\nSolution is here: Lauren's husband took a long hot bath when he got home.\nExplanation: If a person takes a bath, another person's tiredness is not reduced.\n\nNow, solve this: Beginning: Shay was hiking in the woods. Middle: Shay was found to be an good survivor after she found an waypoint. Ending: Shay felt overwhelming relief.\nSolution:" }, { "from": "gpt", "value": "Shay was a good survivor but she never found a waypoint." } ]
[ { "from": "human", "value": "TASK DEFINITION: The input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Given such a dialogue, output the price range the user if looking for which can take one of four values: Cheap, Moderate, Expensive and Don't Care. Output cannot be any other value than the four values. Note that if the user asks for the prices of items provided at a pub, restaurant or coffee shop but doesn't mention the price range they are looking for then the correct classification will be Don't Care. If the user does not mention a particular price, the correct classification will be Don't Care.\nPROBLEM: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'can i have an expensive east asian restaurant'\nSystem: 'Shiraz, which serves east asian food, is a great restaurant. It's in the expensive price range.'\nUser: 'can i have the address please'\nSystem: 'Shiraz is located on 84 Regent Street.'\nUser: 'can i have the phone number please'\nSystem: 'The phone number of Shiraz is 01223902104.'\nUser: 'can i have the price range'\nSystem: 'Shiraz is a great venue. The price for main courses ranges from 9 pounds to 14 pounds 15.'\nUser: 'background noise'\nSystem: 'Shiraz is an outstanding restaurant, it serves east asian food and it's in the expensive price range.'\nUser: 'can i have the price venue'\nSystem: 'Shiraz is an outstanding venue. The price for main courses ranges from 9 pounds to 14 pounds 15.'\nUser: 'thank you good bye'\n\n\nSOLUTION: Expensive\n\nPROBLEM: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'sil'\nSystem: 'What kind of price range are you looking for? For example, expensive, or moderate.'\nUser: 'sil'\nSystem: 'What kind of price range are you looking for? For example, cheap, free, or moderate.'\nUser: 'moderate'\nSystem: 'What kind of venue are you looking for? For example, a cafe, a pub, or a restaurant.'\nUser: 'dont care'\nSystem: 'What kind of venue are you looking for? For example, a restaurant.'\nUser: 'vegetarian restaurant'\nSystem: 'The Rainbow Cafe, which serves traditional and vegetarian food, is a great restaurant. It's in the moderate price range.'\nUser: 'restaurant'\nSystem: 'The Rainbow Cafe, which serves traditional and vegetarian food, is an outstanding restaurant. It's in the moderate price range.'\nUser: 'what is the phone number and price of the venue'\nSystem: 'The phone number of the Rainbow Cafe is 01223321551. The price for main courses ranges from 7 pounds 95 to 10 pounds 95 and the price for a cappuccino is 1 pound 75.'\nUser: 'what is the phone number'\nSystem: 'The phone number of the Rainbow Cafe is 01223321551.'\nUser: 'thank you have a good day'\nSystem: 'Can I help you with anything else?'\nUser: 'sil'\nSystem: 'Can I help you with anything else?'\nUser: 'sil'\nSystem: 'The Rainbow Cafe is a great restaurant.'\nUser: 'thank you have a good day'\n\n\nSOLUTION: Don't Care\n\nPROBLEM: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'im looking for an expensive restaurant in the fenington area'\nSystem: 'What part of town do you have in mind? For example, something in the Barnwell, New Chesterton, or Trumpington area.'\nUser: 'fen ditton'\nSystem: 'What part of town do you have in mind? For example, something in the Addenbrooke's, central, or Romsey area.'\nUser: 'area'\nSystem: 'What part of town do you have in mind? For example, something in the Barnwell, New Chesterton, or Trumpington area.'\nUser: 'feninton'\nSystem: 'What part of town do you have in mind? For example, Barnwell.'\nUser: 'fen ditton'\nSystem: 'What part of town do you have in mind? For example, something in the Addenbrooke's, Barnwell, or Chesterton area.'\nUser: 'thank you good bye'\n\n\nSOLUTION:" }, { "from": "gpt", "value": "Expensive\n\n" } ]
[ { "from": "human", "value": "Q: In this task, you're given a review from Amazon's food products. 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 or mixed, 4: good, 5: extremely good. \nThis is not a gourmet chocolate chip cookie, but is the best chocolate chip cookie that we have found in the grocery store. It is not too firm or soft, has a good amount of flavorful chocolate chips, and makes for a nice snack or dessert. We have eaten these for years in my house.\nA:" }, { "from": "gpt", "value": "5" } ]
[ { "from": "human", "value": "Instructions: Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\nInput: After reading Schoemperlen's Language of Love I couldn't wait to read her new book. I was NOT disappointed. All of the magic and insight and wonder and irony is there. Later when I took a walk on the beach, everything seemed magnified. The sun and a grain of sand were suddenly about the same size and equally amazing.\nOutput:" }, { "from": "gpt", "value": "Positive" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, five ordered key facts are given. All the given facts are expressed in natural language. Your job is to generate a story 100 to 1000 words long, that includes all the facts given as input in their order of appearance while expanding upon them to produce a broader, yet coherent, narrative.\nProblem:Fact1: Matthew Matt Scudder is in car with partner, Fact2: partner urges him to get help, Fact3: kidnappers directed him to car containing wife 's dismembered body, Fact4: Matt forces him to remember finding bags containing parts of Leila in cemetery pond, Fact5: Matt talks to Leila 's fiance drag her into van driven by third person\nSolution:" }, { "from": "gpt", "value": "In 1991, Detective Matthew Matt Scudder Liam Neeson is in a car with his partner, who urges him to get help and expresses his concern that Scudder is not a reliable backup. Scudder then enters a bar and buys drinks with a coffee. Two armed men come in and kill the bartender, and Matt fatally shoots one assailant. He pursues and kills the second assailant, as well as their getaway driver. Eight years later, a drug addict named Peter Kristo Boyd Holbrook approaches Matt, now retired, and asks him to help his brother Kenny Kristo Dan Stevens. Kenny is a drug trafficker whose wife was kidnapped and murdered. Kenny told Matt that after he delivered the ransom, the kidnappers directed him to a car containing his wifes dismembered body. Matt ultimately agrees to find the kidnappers. At the library, Matt researches similar killings, and finds victims named Marie Gotteskind and Leila Anderssen. He meets a homeless youth named TJ Brian Astro Bradley, who helps with his search. Based on an article, Matt goes to a cemetery and speaks with the groundskeeper, Jonas Loogan Olafur Darri Olafsson, who is upset that Matt forces him to remember finding bags containing parts of the dismembered Leila in the cemetery pond. Matt talks to Leilas fiance Reuben Mark Consuelos, who claims to have witnessed two men drag her into a van driven by a third person. Out the window, Matt sees Jonas exiting an apartment building. In a tool shed belonging to Jonas on the buildings roof, Matt finds photos of Reuben and Leila having sex. Jonas admits that he helped kidnap Leila. He had conspired to take Leila away from Reuben, who is a drug dealer, and help her stop using drugs. Instead, however, the other two men tortured and killed Leila. Jonas gives Matt one name Ray and jumps off the roof to his death. The two kidnappers, Ray David Harbour and Albert Adam David Thompson, scout the home of Yuri Landau Sebastian Roche, another drug trafficker. After realizing Landaus wife is bedridden, they prepare to leave for a new target. However, they see his 14yearold daughter Lucia Danielle Rose Russell, and Ray decides to kidnap her. Matt eventually learns that Marie was a DEA agent and realizes that the people who murdered her also got her files, which they have been using to choose their victims. Meanwhile, Matt grows closer to TJ, and encourages the boy to study to avoid a life of crime. During a conversation with TJ, Matt explains why he retired. During the shootout from the opening scene, one of his bullets killed a 7yearold girl. He has been sober ever since. Kenny brings Matt to Landaus home, where the kidnappers call and arrange a drop. Matt, Kenny, Landau, Peter, and TJ who earlier brought Matt his old gun go to the cemetery. After a stand off, Lucia, with a finger hurt down to the bone, is returned to her father. When Albert realizes the ransom money is counterfeit, a shootout ensues. Peter is killed, and Matt wounds Ray. Albert and Ray escape in their van. After Albert and Ray arrive at their place, TJ sneaks out of their van, calls Matt, and tells him the address. Albert garrottes Ray in the basement, and goes back upstairs to find Matt, Kenny, and TJ. Matt overpowers and cuffs Albert. He leaves Albert for Kenny and calls a cab for TJ. While Kenny goes down in the basement, Albert frees himself. Matt goes back inside the house and finds Kennys corpse. Albert attacks Matt, and after a brief fight, Matt kills him. Matt returns home to find TJ sleeping on the couch and spots a drawing that TJ made of himself as a superhero. He sits down and falls asleep." } ]
[ { "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 count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\n\n['7233', 'w', 'W', '1575', 'N', '749', '2983']\n4\n\n['V', 'S', 'i', 'g', '9667', '1271', '9327', '2915', '5993', 'f', 'd', '3347', 'a', '27', '8721', '4855', 'M', '9401', '8797', 'K', '8609']\n12\n\n['m', '4095', 'o', 'i', '9291', '7443', 'z', '9811', '2101', 'H', '3261', 'S', '3853', '2017', '7013', 'Q', '3551', '9853', 'F', 'd', '5693', '2381', '8865', '3777', 'T', '8149', '9157', '231', '9229', 'Z', '7663', 'H', 'P', 'k', 'Y', '3023', '5179', 'z']\n" }, { "from": "gpt", "value": "22\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a review from Amazon and your task is to generate the name of the category of the product based on the review given by the user. The categories are: kitchen, office product, watch, wireless, other, toy, digital video download, camera, jewelry, pet products, sports, industrial supplies, baby product, grocery, drugstore, home improvement, pc, shoes, automotive, digital ebook purchase, musical instruments, beauty, book, electronics, lawn and garden, apparel, home, video games, luggage, furniture, personal care appliances.\nSee one example below:\nProblem: Arrived broken. Manufacturer defect. Two of the legs of the base were not completely formed, so there was no way to insert the casters. I unpackaged the entire chair and hardware before noticing this. So, I'll spend twice the amount of time boxing up the whole useless thing and send it back with a 1-star review of part of a chair I never got to sit in. I will go so far as to include a picture of what their injection molding and quality assurance process missed though. I will be hesitant to buy again. It makes me wonder if there aren't missing structures and supports that don't impede the assembly process.\nSolution: furniture\nExplanation: The customer gives a review of the product which belongs to the furniture category because we can see it from the way the customer describes his experience sharing how he unpackaged his chair.\n\nProblem: Can I please return the security system for another wireless one . I was moving in my house and bought this over Christmas and I thought it was wireless. It has not been used and is only opened to see that it was not wireless. The box and everything is deceiving . There is NO description or pictures of wire's . I will purchase the difference of another security system and return this one. I didn't move in till February. Thank you\nSolution:" }, { "from": "gpt", "value": "camera" } ]
[ { "from": "human", "value": "Teacher: Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nWhich writer rode Devon Loch in the 1956 Grand National?\nSolution: dick francis\nReason: The answer is precise and accurately answers the question based on a fact. This is a good example\n\nNow, solve this instance: One of the 'Seven Wonders of the Ancient World' was the Mausoleum at Halicarnassus. Near which modern tourist resort is the site located?\nStudent:" }, { "from": "gpt", "value": "bodrum" } ]
[ { "from": "human", "value": "Definition: In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\nInput: Context: Jan gave Bailey another chance after they cheated on them last summer. \n Question: Why did Jan do this? \n Options: (A) dying of flu (B) felt a soft spot for them (C) honest\nOutput:" }, { "from": "gpt", "value": "C" } ]
[ { "from": "human", "value": "In this task, you need to count the number of times the given letter appears in the given sentence.\n\nLet me give you an example: Sentence: 'a large group of bananas proped up on several bicycles'. Find frequency of the letter 'e'\nThe answer to this example can be: 5\nHere is why: The letter 'e' appears 5 times in the sentence.\n\nOK. solve this:\nSentence: 'there is a male surfer in the ocean riding a wave'. Find frequency of the letter 'r'\nAnswer:" }, { "from": "gpt", "value": "4" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a question and answer for that. The answer will fill in the blank or will complete the unfinished question. Your task is to provide an explanation based on the given question or fill-in-the-blank statement, and answer.\nPart 2. Example\nQuestion: The government of Canada is considering implementing less carbon taxes across the country. If these taxes were implemented, the amount of carbon dioxide emissions in the country would be expected to \n Answer: rise\nAnswer: The carbon taxes encourage people to use less fossil fuel, which reduces carbon dioxide emissions.\nExplanation: As mentioned in the input Question and Answer, the output statement constructs the explanation correctly. By decreasing the taxes, carbon dioxide emissions will rise, so the explanation is correct. \nPart 3. Exercise\nQuestion: Dan is watching the ship leave the dock. While the ship is near him, it is massive. However, as the ship floats away, it begins to look \n Answer: smaller\nAnswer:" }, { "from": "gpt", "value": "If you are standing on the shore and a ship is going out to sea, the ship gets smaller as it moves further away from you." } ]
[ { "from": "human", "value": "Given a sentence in Italian, generate a new Italian 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\nIl mondo ha bisogno dell'ordine e della regola dei robot per essere perfetto.\nIl processo ha bisogno della memoria e della regola dei robot per essere realistico.\n\nSe si desidera scrivere una carta termine allora si dovrebbe utilizzare il computer.\nSe si vuole dettare un documento di redazione allora si dovrebbe mettere il computer.\n\nSe si desidera tagliare il suono allora si dovrebbe accedere a uno spettacolo.\n" }, { "from": "gpt", "value": "Se sognate di alterare i vostri capelli allora dovreste andare da un professore.\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer.\nPROBLEM: Where does drag me to hell take place?\n\nSOLUTION: Where does drag me to hell take place in the present-day?\n\nPROBLEM: Who were the first european to reach the americas and when did they arrive?\n\nSOLUTION: Who were the first Europeans to reach the Americas?\n\nPROBLEM: Who gave the idea of constituent assembly for india?\n\nSOLUTION:" }, { "from": "gpt", "value": "Who gave the idea of constituent assembly for india by proposing?\n\n" } ]
[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: [589, 561]\nStudent:" }, { "from": "gpt", "value": "[590, 560]" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\n\n['303', '2491']\n" }, { "from": "gpt", "value": "303, 2491" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.\nTeacher: Now, understand the problem? Solve this instance: \"Average families are spending roughly $2,000 more a year on energy costs. ... It's like a $2,000 energy tax in just the last seven years, more than three times what the typical American family received from the Bush tax cuts.\"\nStudent:" }, { "from": "gpt", "value": "energy" } ]
[ { "from": "human", "value": "Teacher:In this task, you will be presented with a passage, and you need to write an implausible answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer. Even though there exist multiple wrong answers, we only need a single wrong answer.\nTeacher: Now, understand the problem? Solve this instance: Ronnie McKinnon paid an emotional tribute to friend and former Rangers team-mate Colin Jackson and insisted that the Ibrox club have lost one of their great servants of the post-war era. McKinnon and Jackson were the defensive rock upon which the foundations for the Light Blues' finest hour in the European Cup Winners' Cup triumph of 1972 was built - although cruel fate was to ensure that both suffered the devastation of watching the final from the sidelines. However, Jackson,who has lost his battle with leukemia at the age of 68, was more than an excellent centre back who contributed greatly to the club's glories in the 1970s. McKinnon described him as a thoroughly decent individual who put others before himself.Ronnie McKinnon has paid tribute to Rangers team-mate Colin JacksonFormer defender Jackson lost his battle with leukemia at the age of 68McKinnon and Jackson were the defensive rock for the club in 1972 \n Question:It was a blessing in disguise as _ was at the heart of one of the great periods in Rangers' history, winning nine major honours in the space of four years.\nStudent:" }, { "from": "gpt", "value": "Ronnie McKinnon" } ]
[ { "from": "human", "value": "Q: In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.\nSet1: '{6, 7, 8, 12, 14, 15, 18, 19}', Set2: '{1, 9, 15, 16, 19}'. Is the element '15' in the intersection of Set1 and Set2 ?\nA:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "In this task you will be given a list of numbers and you should remove all duplicates in the list. If every number is repeated in the list an empty list should be returned. Your list should be numbers inside brackets, just like the given list.\n\nQ: [7, 6, 5, 5, 7, 4, 6, 3, 4]\n\nA: [3]\n**\nQ: [4, 1, 0, 5, 1, 0, 2, 4]\n\nA: [5, 2]\n\nQ: [6, 6, 5, 2, 5, 6, 0, 2]\n\nA:" }, { "from": "gpt", "value": "[0]\n**\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an answer, and your task is to generate a reasonable question for that answer.\nQ: Depends how many you want me to meet.\nA:" }, { "from": "gpt", "value": "Do you want to meet some of my friends?" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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.\n\nSentence: January platinum was down $ 5.70 U {{ an }} ounce at $ 494.50 U . \nWord: an\n" }, { "from": "gpt", "value": "DET" } ]
[ { "from": "human", "value": "Given the prompt and a response, classify the them to \"yes\" if response is \"yes, and\" type. Otherwise classify it as \"no\". \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \n\nQ: Prompt: What percentage is that, honey? Daddy taught you math. \n Response: Don't pity my daddy. He works really hard. He's a man of his own means.\n\nA: no\n**\nQ: Prompt: Now that I think about it, maybe it was an oversight, not to have my phone number on the poster, but I didn't want to give my number out to strangers like these two guys. \n Response: Jason is seeing if we have a less robust arabica. He's checking.\n\nA: no\n\nQ: Prompt: I have got to get to the States. They have freedoms we have not even dreamed of here. \n Response: I know it's fat, but it looks like biceps.\n\nA:" }, { "from": "gpt", "value": "no\n**\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.\nPROBLEM: Sentence1: Refraction is the bending of light. \nSentence2: a rainbow is formed by bending of light by separating light into all different colors.\n\nSOLUTION: bending\n\nPROBLEM: Sentence1: being burried under soil and mud changes peat into coal through extreme heat and pressure in a swamp over a long period of time. \nSentence2: Marble is used for sculptures, and coal is used for fuel and energy like light.\n\nSOLUTION: coal\n\nPROBLEM: Sentence1: a cavern is formed by carbonic acid in groundwater seeping through rock and dissolving limestone. \nSentence2: Carbonic acid dissolves limestone by separating the calcium and carbonate and creating a liquid.\n\nSOLUTION:" }, { "from": "gpt", "value": "carbonic\n\n" } ]
[ { "from": "human", "value": "In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise.\n\nExample input: Sentence 1: The sum of all chemical reactions that take place within an organism is known as metabolism. Sentence 2: Metabolism is the sum total of all chemical reactions performed by an organism.\nExample output: entails\nExample explanation: Sentence 2 gives out supporting information about the Metabolism hence it is correct\nQ: Sentence 1: The name of film that polyester fibers form is mylar. Sentence 2: Mylar® is a trademark of DuPont for its brand of polyester thick film.\nA:" }, { "from": "gpt", "value": "entails" } ]
[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nOne example: 6, 14, ['9545', '5185', '1667', 'w', 's', '9559', 'T', 'u', 'U', '6843', 'L', 'l', '6365', '7103', 'A', '2381', '5037', 'X', '4487', 'd']\nSolution is here: 9559TuU6843Ll63657103\nExplanation: Here, concatenating all the elements between the 6th element and 14th element gives '9559TuU6843Ll63657103'.\n\nNow, solve this: 2, 16, ['5271', 'H', 'z', 'M', '2793', 'h', 'C', 'J', '3517', 'Q', 'R', 'm', 'j', 'p', '1461', 'U', 'Q', 'P', '7079', '4695', '4029', '8635', 'x']\nSolution:" }, { "from": "gpt", "value": "HzM2793hCJ3517QRmjp1461U" } ]
[ { "from": "human", "value": "Instructions: Given a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nInput: Charlotte entered the bathroom. Ethan entered the bathroom. The grapefruit is in the green_basket. Ethan exited the bathroom. Charlotte moved the grapefruit to the red_envelope. Charlotte exited the bathroom. Ethan entered the bathroom. Where was the grapefruit at the beginning?\nOutput:" }, { "from": "gpt", "value": "green_basket" } ]
[ { "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 title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story and their positions in the sentence order of the story; note that the selected choices may fit into the story at any point. Your answer must be in the form of '2a, 5b', where '2a' means the candidate sentence 'a' will be inserted as the 2nd sentence in the story. The answer must also be in the order of the selected choices, i.e., '2a, 5b' is allowed, and '5b, 2a' is not allowed. If options are equally plausible, pick the ones that make more sense.\n\nTitle: Marcus Buys Khakis. Marcus needed clothing for a business casual event. He decided to buy a pair of khakis. The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked. c. All of his clothes were either too formal or too casual.\nSolution: 5a, 2c\nWhy? Marcus is buying clothes for a business event and not presenting an idea.\n\nNew input: Title: Stephen was always afraid of bears. One day, he found one when he went camping. The bear was sleeping very soundly. Choices: a. Now, Coleman can charge his phone. b. Stephen accidentally woke the bear up. c. After that, Stephen had to run away as fast as possible.\nSolution:" }, { "from": "gpt", "value": "4b, 5c" } ]
[ { "from": "human", "value": "Definition: In this task, you are given a question, and your task is to predict the context of the question. We assume that someone named X asked the question from Y. The context of the question means the previous situation that led X to ask this question.\nInput: Are you a fan of movie soundtracks?\nOutput:" }, { "from": "gpt", "value": "X wants to know about Y's music preferences." } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.\nInput: Statement: yeah and uh when you have time to do it Choices: 1. When you have time to do it you should check out Burger Kind deals. 2. When you don't have time to do that, no. 3. When you have time to do it.\nOutput:" }, { "from": "gpt", "value": "2" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you will be given a list of integers. A list contains numbers separated by a comma. You need to round every integer to the closest power of 2. A power of 2 is a number in the form '2^n', it is a number that is the result of multiplying by 2 n times. The following are all powers of 2, '2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096'. If an integer is exactly in equally far from two different powers of 2 then you should output the larger power of 2. The output should be a list of integers that is the result of rounding each integer int the input list to the closest power of 2. The output should include a '[' to denote the start of the output list and ']' to denote the end of the output list.\n\n[211, 1919, 3792, 1661, 8, 49, 3, 96, 395, 3847, 1697, 16, 43, 4, 104, 834]\nOutput:" }, { "from": "gpt", "value": "[256, 2048, 4096, 2048, 8, 64, 4, 128, 512, 4096, 2048, 16, 32, 4, 128, 1024]" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a statement spoken by a politician in natural language and the subject of the discussion for the given statement. Your task is to determine if the given subject of the discussion is correct for the given statement. The subject can be multiple words. Answer with \"True\" if it's the correct subject of discussion or return \"False\" if it's incorrect.\n\nStatement: The \"pay-as-you-go law ... was a big reason why we had record surpluses in the 1990s.\" \n Subject: education\nOutput:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you must classify if a given review is positive/negative, indicating your answer as P or N.\nPart 2. Example\nplot : two teen couples go to a church party , drink and then drive .\nthey get into an accident .\none of the guys dies , but his girlfriend continues to see him in her life , and has nightmares .\nwhat 's the deal ?\nwatch the movie and \" sorta \" find out . . .\ncritique : a mind - fuck movie for the teen generation that touches on a very cool idea , but presents it in a very bad package .\nwhich is what makes this review an even harder one to write , since i generally applaud films which attempt to break the mold , mess with your head and such ( lost highway & memento ) , but there are good and bad ways of making all types of films , and these folks just did n't snag this one correctly\n.\nthey seem to have taken this pretty neat concept , but executed it terribly .\nso what are the problems with the movie ?\nwell , its main problem is that it 's simply too jumbled\n.\nit starts off \" normal \" but then downshifts into this \" fantasy \" world in which you , as an audience member ,\nhave no idea what 's going on\n.\nthere are dreams , there are characters coming back from the dead , there are others who look like the dead , there are strange apparitions , there are disappearances , there are a looooot of chase scenes , there are tons of weird things that happen , and most of it is simply not explained .\nnow i personally do n't mind trying to unravel a film every now and then , but when all it does is give me the same clue over and over again , i get kind of fed up after a while , which is this film 's biggest problem .\nit 's obviously got this big secret to hide , but it seems to want to hide it completely until its final five minutes .\nand do they make things entertaining , thrilling or even engaging , in the meantime ?\nnot really .\nthe sad part is that the arrow and i both dig on flicks like this , so we actually figured most of it out by the half - way point , so all of the strangeness after that did start to make a little bit of sense , but it still did n't the make the film all that more entertaining .\ni guess the bottom line with movies like this is that you should always make sure that the audience is \" into it \" even before they are given the secret password to enter your world of understanding .\ni mean , showing melissa sagemiller running away from visions for about 20 minutes throughout the movie is just plain lazy ! !\nokay , we get it .\n. .\nthere are people chasing her and we do n't know who they are .\ndo we really need to see it over and over again ?\nhow about giving us different scenes offering further insight into all of the strangeness going down in the movie ?\napparently , the studio took this film away from its director and chopped it up themselves , and it shows .\nthere might 've been a pretty decent teen mind - fuck movie in here somewhere , but i guess \" the suits \" decided that turning it into a music video with little edge , would make more sense .\nthe actors are pretty good for the most part , although wes bentley just seemed to be playing the exact same character that he did in american beauty , only in a new neighborhood .\nbut my biggest kudos go out to sagemiller , who holds her own throughout the entire film , and actually has you feeling her character 's unraveling .\noverall , the film does n't stick\nbecause it does n't entertain , it 's confusing , it rarely excites and\nit feels pretty redundant for most of its runtime , despite a pretty cool ending and explanation to all of the craziness that came before it .\noh ,\nand by the way , this is not a horror or teen slasher flick . . .\nit 's just packaged to look that way because someone is apparently assuming that the genre is still hot with the kids .\nit also wrapped production two years ago and has been sitting on the shelves ever since .\nwhatever . .\n. skip it !\nwhere 's joblo coming from ?\na nightmare of elm street 3 ( 7/10 ) - blair witch 2 ( 7/10 ) - the crow ( 9/10 ) - the crow : salvation ( 4/10 )\n- lost highway ( 10/10 ) - memento ( 10/10 ) - the others ( 9/10 ) - stir of echoes ( 8/10 )\nAnswer: N\nExplanation: The phrases used in the review convey a negative sentiment (e.g. \"presents it in a very bad package\").\nPart 3. Exercise\nnearly every film tim burton has directed has been an homage to the horror genre -- \" frankenweenie , \" \" beetlejuice , \" \" batman ,\n\" \" edward scissorhands , \" \" ed wood , \" \" mars attacks !\n\" -- yet none of them have been horror films .\n\"\nsleepy hollow \" is his first attempt to actually scare people .\ni greeted the prospect with high anticipation ; burton 's whole career seemed to be leading up to this .\ni left disappointed .\nandrew kevin walker 's screenplay takes only the character names from the classic short story \" the legend of sleepy hollow .\n\" in the movie ichabod crane ( johnny depp ) is a new york city police constable who is trying to introduce scientific methods of investigation to his superiors .\nichabod is dispatched to the small town of sleepy hollow to investigate a series of murders .\nseveral of the town 's leading citizens have been decapitated by the headless horseman .\nalthough he rejects the ghost story the town elders tell him , ichabod finds that the facts of the case confound his scientific reasoning .\nhe also discovers that the killings are not random , that the victims are tied together by a secret .\nalong the way ichabod gets help from a bewitching ( literally ) young woman ( christina ricci ) and the son of one of the murder victims ( marc pickering ) .\nmy reaction : ho - hum\n.\nthe plot is an accumulation of cliches without even the slightest touch of originality to make it interesting .\nthat in itself is forgivable ; hollywood constantly tries to sell us used products in new packages .\nhowever , burton 's attempts at inducing fright come off as goofy .\nit might be his background -- in his previous movies , goofy was the goal .\nalong the same lines , it does n't help that creature designer ( and producer ) kevin\nyagher has done his best work for the tongue - in - cheek tales from the crypt tv series .\na witch 's eyes and tongue shoot out like roger rabbit 's , a tree spurts blood like it 's in a monty python sketch , and\nthe headless horseman .\n. .\nwell , he 's a guy without a head .\n.\n.\non a horse\n( boo ! ) .\nthe performances are also awful .\nalthough he 's impressed me with his work in other films , depp does n't seem to know what to do with ichabod , and his dialogue is hampered by stilted diction\nthat 's supposed to pass for an 18th century accent .\nricci seems to put all her effort into seeming enigmatic , which guarantees that we wo n't sympathize with her character .\nthe actor who is revealed at the end to be the villain comes off as ridiculously cartoonish .\nthe only pleasure generated by the cast comes from surprise cameos by christopher lee , martin landau , and christopher walken .\ni wonder if this movie was originally conceived as part of francis ford coppola 's projected series of gothic adaptations , a series that produced only \" bram stoker 's dracula \" and \" mary shelley 's frankenstein .\n\"\ncoppola is an executive producer for \" sleepy hollow , \" and the script reflects his interest in early forms of \" moving pictures , \" particularly in a toy that ichabod carries which blends two pictures to create an optical illusion .\n( there 's a bird on one side of the card , a cage on the other .\nwhen the card is flipped rapidly , the bird appears to be caged . )\nbottom line : the hollow is n't the only thing that 's sleepy .\nAnswer:" }, { "from": "gpt", "value": "N" } ]
[ { "from": "human", "value": "Definition: You are given a science question (hard-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\nInput: How much time is required for a bicycle to travel a distance of 100 m at an average speed of 2 m/s? \n (A) 0.02 s (B) 50 s (C) 100 s (D) 200 s\nOutput:" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "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'. \nExample: news:According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing .\npolarity:neutral\nExample solution: true\nExample explanation: 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\nProblem: news:When cruising , the revs fall as less engine output is required .\npolarity:positive\n" }, { "from": "gpt", "value": "Solution: false" } ]
[ { "from": "human", "value": "In this task, you need to count the number of words in a sentence that contain the given letter\n\n[Q]: Sentence: 'a man and a woman stand under an umbrella'. How many words contain the letter 's' in the sentence.\n[A]: 1\n\n\n[Q]: Sentence: 'a picture of some horses and a person in the street'. How many words contain the letter 'r' in the sentence.\n[A]: 4\n\n\n[Q]: Sentence: 'a bathroom with large brown tiles and white fixtures'. How many words contain the letter 'b' in the sentence.\n[A]:" }, { "from": "gpt", "value": "2\n\n\n" } ]
[ { "from": "human", "value": "In this task, you need to answer basic science questions. For each question, several terms are intentionally masked with *. This masking can cover very few or many of the question words. Clearly, if masked terms are important, the modified question will be impossible to answer. Please indicate the correct answer with one of the following responses: \"A\", \"B\", \"C\", \"D\" or \"E\". While \"A\"-\"D\" correspond to the answer options provided in the input, \"E\" represents \"I don't know\" for questions that do not provide enough information. Respond via \"E\" if the question is not answerable. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E'.\n--------\nQuestion: Question: Which physical * do some * have that helps them * in the Arctic? (A) growing tall to hide in trees (B) changing fur color to hide from predators (C) developing large paws to protect themselves from the wind (D) producing shallow root systems to protect themselves from the cold ai.\n\nAnswer: E.\n\n\nQuestion: Question: * known * *** are made up of ___. (A) eggs (B) cells (C) cell walls (D) gelati.\n\nAnswer: E.\n\n\nQuestion: Question: Which of the following statements about food and oxygen is true? (A) Only specialized structures require food and oxygen. (B) Every cell requires food and oxygen. (C) Only plant cells require food and oxygen. (D) Cells do not require food and oxygen because they are not living things.\n\nAnswer:" }, { "from": "gpt", "value": "B.\n\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\nInput: Sentence1: 'a woman on skis holding one hand up with a pole', Sentence2: 'there are two boys playing soccer with a woman'. Is the frequency of the word 'with' in two sentences equal?\nOutput:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Part 1. Definition\n\"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange.\nPart 2. Example\nPrompt: See, Arlene? That's why I don't talk to you like that because I'm afraid I'll scare our son. \n Response 1: I have 12. Wait, is the key to a success story getting the number to go down? \n Response 2: Oh, Dad. Even that wasn't great.\nAnswer: Response 2\nExplanation: Response 2 is correct answer because it agrees with the prompt and continues the conversation in the same context.\nPart 3. Exercise\nPrompt: Now that we've got that all straightened out, what did you want to say, Daniel? Jacket-less. \n Response 1: You know what? I'll put on a jacket if it'll make you happy. \n Response 2: OK. I got those baked lays you wanted.\nAnswer:" }, { "from": "gpt", "value": "Response 1" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'.\n\nSentence 1: Andy wanted to incorporate some vegetables into his daughter's dinner. Sentence 2: Andy decided he would put mixed vegetables into her macaroni. Sentence 3: Andy mixed the food together, and gave her the food. Sentence 4: However, Andy's daughter immediately told him she did not want it. Sentence 5: Andy knew she did not want it because of the vegetables in there. Choices: a. Mixed Vegetables. b. Peanut butter cups.\n" }, { "from": "gpt", "value": "a" } ]
[ { "from": "human", "value": "You are given a target profession, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\n--------\nQuestion: Target: producer \nI don't actually know what a producer does. They have lots of money.\n\nAnswer: stereotype\n\n\nQuestion: Target: assistant \nThe assistant came into work late. Greenland is probably not for sale.\n\nAnswer: unrelated\n\n\nQuestion: Target: chess player \nA chess player sat next to me on the bus. My socks are made of bamboo.\n\nAnswer:" }, { "from": "gpt", "value": "unrelated\n\n\n" } ]
[ { "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 will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'sottrazione'.\n\n10 sottrazione 7\nSolution: 3\nWhy? Here, 'sottrazione' represents the subtraction operation. So, the answer is 3 (10-7=3).\n\nNew input: 4867 sottrazione 5686 aggiunta 8014\nSolution:" }, { "from": "gpt", "value": "7195" } ]
[ { "from": "human", "value": "Detailed Instructions: Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nQ: Kingston is the capital of which country?\nA:" }, { "from": "gpt", "value": "jamaica" } ]
[ { "from": "human", "value": "You are provided with an \"Event\", \"Intent\" and \"XEmotion\" (PersonX's reactions for the given \"Event\"). Indicate PersonY's reaction (person feels) at the end of this event. Provide one reaction for PersonY. If there's nothing that can be implied, respond as None\n--------\nQuestion: Event:PersonX eventually found out. Intent: 1) to have a new car.. XEmotion: 1) great.\n\nAnswer: also happy\n\n\nQuestion: Event:PersonX enjoys it very much. Intent:. XEmotion:\n\nAnswer: happy\n\n\nQuestion: Event:PersonX takes ___ to disneyland. Intent: 1) take to show particular ones skils. XEmotion: 1) happy 2) enjoyed\n\nAnswer:" }, { "from": "gpt", "value": "excited\n\n\n" } ]
[ { "from": "human", "value": "Instructions: You are given a science question (easy-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\nInput: Which concept was most likely modified due to the invention of the microscope? \n (A) size of subatomic particles (B) composition of living things (C) number of the moons of Jupiter (D) formation of sedimentary rocks\nOutput:" }, { "from": "gpt", "value": "B" } ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.