Search is not available for this dataset
conversations
listlengths 2
2
|
---|
[
{
"from": "human",
"value": "instruction:\nIn this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively.\nquestion:\nPremise: A young red-haired woman uses a scope to scout out shooting targets on a gun range.\nHypothesis: The woman is shooting with other people at the range\nUpdate: The woman is surrounded by other people with guns\nanswer:\nstrengthener\n\n\nquestion:\nPremise: A large crowd standing in front of a very large painting.\nHypothesis: A crowd is looking at a painting.\nUpdate: The crowd is paying attention to a mime that is performing in front of the painting.\nanswer:\nweakener\n\n\nquestion:\nPremise: Two people are using tools to dig in a pit while a person wearing a cowboy hat looks on.\nHypothesis: Two people are using tools to dig in a pit while a tall person wearing a cowboy hat looks on.\nUpdate: The person with the cowboy hat is 6 years old.\nanswer:\n"
},
{
"from": "gpt",
"value": "weakener\n\n\n"
}
] |
[
{
"from": "human",
"value": "instruction:\nYou are given an elementary science question along with a few answer options. List all the words from the question that are essential and sufficient for choosing the correct answer option. Keep in mind that essential words are necessary to understand the meaning of the given question. However, non-essential words provide little information needed to select the correct answer. You can think about it like this: If the question was in another language, knowing the meaning of which words were necessary and enough for you to understand the question and answer it?. If your answer consists of multiple spans of words from the question, separate those using a comma (\", \"). Do not generate any word that is not present in the question. Make sure that your response is contained in the given question and the words are in the same order as the question.\n Grammatical correctness is not important.\nquestion:\nQuestion: Carbon dioxide is necessary for photosynthesis to happen. How do plants absorb carbon dioxide from the atmosphere? (A) Through the petals (B) Through the stigma (C) Through the stomata (D) Through the stem?\nanswer:\nplants, absorb, carbon, dioxide, atmosphere?\n\n\nquestion:\nQuestion: Using fossil fuels wisely and avoiding waste is an example of (A) rationing. (B) recycling. (C) substitution. (D) conservation.?\nanswer:\nfossil, fuels, wisely, avoiding, waste\n\n\nquestion:\nQuestion: Which of these cycles takes 24 hours? (A) Earth rotating on its axis (B) Earth revolving around the Sun (C) the Moon rotating on its axis (D) the Moon revolving around Earth?\nanswer:\n"
},
{
"from": "gpt",
"value": "cycles, takes, 24, hours?\n\n\n"
}
] |
[
{
"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.\nQ: Category: bird \nWords: derrick, excavator, crane, hummingbird, tackle\nA: "
},
{
"from": "gpt",
"value": "excavator"
}
] |
[
{
"from": "human",
"value": "In this task, you're given an open-domain question. Your task is to provide an answer to the given question. There is only one unique answer for each question. Your answer should be short, and refer to an entity, date, number, etc. Do not put your answer in the context of a sentence.\n\nWhich amendment separated the vote for president and vice president?"
},
{
"from": "gpt",
"value": "Twelfth Amendment"
}
] |
[
{
"from": "human",
"value": "In this task, you're given context and an answer. Your task is to generate the question for this answer based on the given context with commonsense reasoning about social situations..\n\nContext: Lee played tag and got first place after a few tries. \n Answer: strong"
},
{
"from": "gpt",
"value": "What will happen to Lee?"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.\nQ: How did Arizona come about?\nA:"
},
{
"from": "gpt",
"value": "user"
}
] |
[
{
"from": "human",
"value": "Instructions: Given a sentence, an entity and its sentiment towards the entity, verify if it is the correct sentiment towards the entity. Answer should be yes or no. Note that URLs in the text have been replaced with [Link].\nInput: Verify if the sentiment of the following document towards the entity Cristiano Ronaldo is Neutral . Daniel Carvajal responded with a fine solo effort and Ronaldo also came close a little later but the Spaniards were lucky not to concede a penalty when Ramos cleared a Maximilian Philipp effort on the line with his hand.\nOutput:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given a statement, further information available on a particular linked term from the statement, and a question. Your job is to generate the answer to the question by using the information provided. If there is no clear answer obtainable, output 'none'.\nContext: \"Written in the Stars\" was used by Major League Baseball for their commercials Link Information: It was also chosen by WWE as its theme song for WrestleMania XXVII Question: Which American sport organization that used \"Written in the Stars\" had been in operation first?\nA:"
},
{
"from": "gpt",
"value": "Answer: Major League Baseball"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\nQ: password = QGQ1NZgSY.noe5WwiS9ykk4pJ.!58aGe0om9Occ\nA:"
},
{
"from": "gpt",
"value": "19"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task you are expected to provide an SQL statement from an english description of what that SQL statement does. The description may include multiple steps but you should only ouput one SQL statement that accomplishes every step. An SQL query works by selecting data from a table where certain conditions apply. A table contains columns where every row in that table must have a value for each column. Every table has a primary key that uniquely identifies each row, usually an id. To choose which columns are returned you specify that after the \"SELECT\" statement. Next, you use a \"FROM\" statement to specify what tables you want to select the data from. When you specify a table you can rename it with the \"AS\" statement. You can reference that table by whatever name follows the \"AS\" statement. If you want to select data from multiple tables you need to use the \"JOIN\" statement. This will join the tables together by pairing a row in one table with every row in the other table (Cartesian Product). To limit the number of rows returned you should use the \"ON\" statement. This will only return rows where the condition specified after the statement is true, this is usually an equals operator with primary keys. You can also use the \"WHERE\" statement to specify that only rows with column values statisfying a certain condition, should be returned. The \"GROUP BY\" statement will group rows together that have equal column values for whatever columns follows the statement. The \"HAVING\" statement will return groups that statisfy whatever condition follows the statement. Any column(s) being returned from grouped rows must either be an aggregate function, (AVG, MAX, COUNT, SUM, ...) of a column, or the column(s) that the data was grouped by. To sort the returned data you can use the \"ORDER BY\" command which will order the data by whatever aggregate function or column follows the statement. The \"DESC\" statement will sort in descending order and the \"ASC\" statement will sort in ascending order. Finally, you can use the \"LIMIT\" statement to return a certain number of rows. When \"*\" is used in an SQL statement every column is returned. For example, SELECT * FROM table WHERE attribute = 1, will select every column from rows with the attribute column equal to 1.\nInput: Step 1: find the number of rows of each value of Name in member table.\nStep 2: find Name of member table ordered descending by the results of step 1.\nStep 3: only show the first 3 rows of the results\nOutput:"
},
{
"from": "gpt",
"value": "SELECT Name FROM member GROUP BY Name ORDER BY Count ( * ) Desc LIMIT 3"
}
] |
[
{
"from": "human",
"value": "Q: Read the given sentence and if it is a general advice then indicate via \"yes\". Otherwise indicate via \"no\". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.\nToss out the notion that your degree has as much influence over what you do since English is a broad and useful in whatever you decide .\nA:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You have to predict the type of conversation sentence given as input. Your predictions can be one among: 'information' if the input statement states a piece of information, 'question' if the input statement asks for some information, 'directive' if the input sentence involves the management or guidance of operations, and 'commissive' when it constitutes a statement that commits the speaker to some future action.\nProblem: It's a beautiful drive . \nSolution:"
},
{
"from": "gpt",
"value": "information"
}
] |
[
{
"from": "human",
"value": "Q: Given an abstract, indicate which of the provided candidate titles (Option1 and Option2) best describes it (respond with the text of the title, not option1/2).\nAbstract: Endometriosis was induced surgically by implanting pieces of endometrium in the uterine mesenteries of 50 rats. Their fertility was then assessed after various treatments. Ten rats with endometriosis were treated with microsurgical excision of implants, 10 with high-frequency diathermy, 10 with danazol, and 10 with intraperitoneal indomethacin. Ten more rats had implants that were left untreated. The results were compared with those of ten rats that had sham surgery with implantation of fat in the uterine mesenteries. Reproductive performance was better in control animals with sham surgery than in animals with endometrial implants. Maximum restoration of fertility was achieved with indomethacin. Microsurgery and danazol therapy both were effective in preventing residual endometriosis, but the animals tended to be less fertile after treatment. Adhesions were most pronounced after diathermy and least pronounced after microsurgery or indomethacin therapy. In rats treated with indomethacin, persistent endometriotic cysts were invariably smaller near the site of intraperitoneal injection: this suggests a local antiprostaglandin effect. \n Which is the apt title for the abstract? option1: The effect of treatment on experimentally produced endometrial peritoneal implants. option2: Unrecognized responses and feelings of residents and fellows during interviews of patients.\nA:"
},
{
"from": "gpt",
"value": "The effect of treatment on experimentally produced endometrial peritoneal implants."
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. 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 ending, and use names instead of pronouns (e.g. he / she) wherever possible.\nExample: Beginning: Helen lived in the state of Washington. Middle: Helen planned to drive to Canada but it started snowing heavily.\nOutput: Helen stayed home instead and planned to go another day.\nGenerally, people prefer not to drive in bad weather.\n\nNew input case for you: Beginning: The highlight of the zoo visit was the otter exhibit. Middle: Ned paid attention to everything in the exhibit.\nOutput:"
},
{
"from": "gpt",
"value": "Ned learned a lot about otters that day."
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you are given inputs k, i, and A, where k and i are integers and A is a list. You need to find every ith element of A starting from the kth element. The process stops when the position of the next ith element exceeds the length of the list.\nPROBLEM: 1, 2, ['2631', '3691', '329', 'L', 'm', 'p']\n\nSOLUTION: 2631, 329, m\n\nPROBLEM: 3, 1, ['7983', 'r', '3847', '853', '7805', '8161', '3811', '5981', '1189', '5403', 'Y', '6603', 'n', '5837', '9043']\n\nSOLUTION: 3847, 853, 7805, 8161, 3811, 5981, 1189, 5403, Y, 6603, n, 5837, 9043\n\nPROBLEM: 1, 4, ['3895', 'p', '8625', 't', 'm', '4655', 'X', 'Y', '9235']\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "3895, m, 9235\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 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[16, 205, 171, 2, 9, 317]\nSolution: [16, 256, 128, 2, 8, 256]\nWhy? Every integer in the input list is rounded to the nearest power of 2. The number 2 and 16 are in the input list and both are a power of 2, therefore rounding to the closest power of 2 returns the same number. This is a good example.\n\nNew input: [155, 717, 989, 4873, 8]\nSolution:"
},
{
"from": "gpt",
"value": "[128, 512, 1024, 4096, 8]"
}
] |
[
{
"from": "human",
"value": "In this task, you will be shown a sentence, and you should determine whether it is overruling or non-overruling. In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. Classify your answers into overruling or non-overruling\nOne example is below.\nQ: 876 f.3d at 1306.\nA: non-overruling\nRationale: It's a good example. This sentence doesn't overrule any law, So it's non-overruling.\nQ: stowers had a full and fair opportunity to litigate his contempt in those proceedings, all the way through appeal to our court.\nA:"
},
{
"from": "gpt",
"value": "non-overruling"
}
] |
[
{
"from": "human",
"value": "Teacher: You are given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the 5 given options and report that option.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nFrom a pack of 52 cards, two cards are drawn together at random. What is the probability of both the cards being kings? \n\n Option A:2/1223 \n\n Option B: 1/122 \n\n Option C: 1/221 \n\n Option D: 3/1253 \n\n Option E: 2/153 \n\n\nSolution: Option C\nReason: Let s be the sample space. \n Then n(s) = 52C2 = 1326 \n E = event of getting 2 kings out of 4 \n n(E) = 4C2 = 6 \n P(E) = 6/1326 = 1/221\n\nNow, solve this instance: Question: If 12 men do a work in 80 days, in how many days will 20 men do it?\n\n Option A: 18 days\n\n Option B: 38 days\n\n Option C: 42 days\n\n Option D: 48 days\n\n Option E: 44 days\nStudent:"
},
{
"from": "gpt",
"value": "Option D"
}
] |
[
{
"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 a short story of five sentences written in natural language. However, the order of the given story is not correct. Your job is to return the correct order for the given five sentences to create a coherent short story with the new order that has the correct flow. Generate your answer using the number of sentences in the correct order, such as '23415'.\n\nSentence1: He is happy now. Sentence2: Rick grew up in a troubled household. Sentence3: It wasn't long before Rick got shot in a robbery. Sentence4: The incident caused him to turn a new leaf. Sentence5: He never found good support in family, and turned to gangs.\nSolution: 25341\nWhy? Rick grew up in a troubled environment and that made him a join gang. However, one incident of getting caught turned his life.\n\nNew input: Sentence1: No one was watching him so he made an escape. Sentence2: He calmly walked out of the front of the police station. Sentence3: He pushed on it and it opened. Sentence4: No one seemed to notice the suspect. Sentence5: The suspect saw that the cell door was unlocked.\nSolution:"
},
{
"from": "gpt",
"value": "34251"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: 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\nProblem:Event:PersonX finally found PersonY. Intent: 1) to fight for his country. XEmotion: 1) patriotic\nSolution:"
},
{
"from": "gpt",
"value": "thankful"
}
] |
[
{
"from": "human",
"value": "In this task, you need to answer the given multiple-choice question on the general math. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nOne example is below.\nQ: Problem: what is difference between biggest and smallest fraction among 2 / 3 , 3 / 4 , 4 / 5 and 5 / 3 \nOptions: a ) 2 / 5 , b ) 3 / 5 , c ) 1 / 6 , d ) 1 , e ) none of these\nA: d\nRationale: \"explanation : 2 / 3 = . 66 , 3 / 4 = . 75 , 4 / 5 = . 8 and 5 / 3 = 1.66 so the biggest is 5 / 3 and the smallest is 2 / 3 their difference is 5 / 3 - 2 / 3 = 3 / 3 = 1 option d\"\nQ: Problem: what is the 23 th digit to the right of the decimal point in the decimal form of 36 / 66 ? \nOptions: a ) 3 , b ) 4 , c ) 8 , d ) 9 , e ) 6\nA:"
},
{
"from": "gpt",
"value": "b"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nProblem:Sentence 1: Four girls in a kitchen near a plate of brownies. Sentence 2: Four girls in a kitchen.\nSolution:"
},
{
"from": "gpt",
"value": "One of the girls reaches for a brownie."
}
] |
[
{
"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: (1) when the individual's belief matches reality, (2) when the individual's belief does not match reality, (3) is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\n--------\nQuestion: Emily entered the workshop. Logan entered the workshop. The turnip is in the green_box. Emily moved the turnip to the red_box. Where was the turnip at the beginning?\n\nAnswer: green_box\n\n\nQuestion: Alexander entered the kitchen. William entered the kitchen. The turnip is in the blue_box. William exited the kitchen. Alexander moved the turnip to the green_cupboard. Alexander exited the kitchen. William entered the kitchen. Where will William look for the turnip?\n\nAnswer: green_cupboard\n\n\nQuestion: Liam entered the crawlspace. Isabella entered the crawlspace. The eggplant is in the blue_crate. Isabella exited the crawlspace. Liam moved the eggplant to the green_drawer. Where does Liam think that Isabella searches for the eggplant?\n\nAnswer:"
},
{
"from": "gpt",
"value": "blue_crate\n\n\n"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then some input of the task.\nYou are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No.\n\nSentence: Even his Granddaddy was helping out, stuffing melons up into the holes in the tree. \nQuestion: Why did Chip know they weren't getting ready for a party?\nOutput:"
},
{
"from": "gpt",
"value": "No."
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you need to count the number of nouns/verbs in the given sentence.\nInput: Sentence: 'Two signs in the grass outside a building'. Count the number of verbs in this sentence.\nOutput:"
},
{
"from": "gpt",
"value": "0"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an adjective, and your job is to generate its antonym. An antonym of a word is a word opposite in meaning to it.\nExample: accident\nExample solution: purpose\nExample explanation: An accident is unintentional, while purpose involves intention. So the two words have opposite meaning and are hence antonyms.\n\nProblem: rich\n"
},
{
"from": "gpt",
"value": "Solution: plain"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: Given a sentence, generate a most likely context or previous statement. The previous statement should be relevant to the given statement.\nQ: They extend the hand washing to their wrists.\nA:"
},
{
"from": "gpt",
"value": "The person scrubs their hands thoroughly with the soap."
}
] |
[
{
"from": "human",
"value": "In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\n--------\nQuestion: image an of a bench that is set out at the park\n\nAnswer: (1, 2)\n\n\nQuestion: A gray and white cat with stripes that is standing on top of a vehicle rubbing and against an antenna\n\nAnswer: (16, 17)\n\n\nQuestion: One sitting man and the other is standing while holding a conversation\n\nAnswer:"
},
{
"from": "gpt",
"value": "(2, 3)\n\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\n\nReview: I just saw this at the Toronto Film Festival, and I hope it gets wide release because I want to see it again! It is a character-driven film, and Andrew and David are more than up to the task. Any discussion of the plot might beconsidered spoilers, so I'll just say that the storyline is clever, the acting is superb, and the effects are amazing. Well-filmed and well-paced too. One of the best films I have seen in ages, and very refreshing in this summer of drearymovies. It had the audience laughing the whole time. See it if you can. (I particularly liked the \"Candy bar! Candy bar!\" scene.) Question: is it a negative review?\n"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "Given an open-ended topic (movie name, a persons name, an event, sports, etc) generate a simple trivia-type question.\nOne example is below.\nQ: 1968 winter olympics\nA: Which Frenchman won the Alpine triple-crown at the 1968 Winter Olympics?\nRationale: Both these questions ask a specific fact as the answer. So these are valid questions.\nQ: america's next top model\nA:"
},
{
"from": "gpt",
"value": "Which Afro American super model, TV personality and singer hosts the TV show, America's Next Top Model and also has her own daytime TV chat show?"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. 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.\n\nContext: Sydney is a very good palm reader. \n Question: How would you describe Sydney? \n Options: (A) a fraud (B) very accurate (C) ignorant\n"
},
{
"from": "gpt",
"value": "C"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nGiven 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...'. \nPart 2. Example\nPrompt: I'm glad you came into my office today, young man. Look around you. Everything that's in here, I purchased. \n Response: Wow! You own everything in this office?\nAnswer: yes\nExplanation: This is correct answer because response is in support with the prompt and extends the context from prompt.\nPart 3. Exercise\nPrompt: There's a rumor going around that your dad is the Ralph of the grocery store \"Ralphs\". \n Response: I'm pretty sure it was just because of his attitude.\nAnswer:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nIn this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.\nExample: [[7, -3, -3, 11], [-6, -6, -5, 2], [-8, 4, -3]]\nOutput: [0, 72, -32]\nThe first inner list has no even integers, so the first number in the output is 0. The second list has -6, -6, 2 for even integers so the second output is 72. The third list has -8, 4 as even numbers so the third output is -32. This is a good example.\n\nNew input case for you: [[24, 23], [1, -12], [48, -46], [8, -1, -43, 30, 29], [50, -36, 41, 7, 35], [-24, 15, 36, -49], [18, 13], [1, -32]]\nOutput:"
},
{
"from": "gpt",
"value": "[24, -12, -2208, 240, -1800, -864, 18, -32]"
}
] |
[
{
"from": "human",
"value": "Classify given movie review into two categories: positive, or negative based on its content.\n\nthis isn't a stand up and cheer flick ; it's a sit down and ponder affair . and thanks to kline's superbly nuanced performance , that pondering is highly pleasurable ."
},
{
"from": "gpt",
"value": "positive"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view \n 2. only: returns whether there is exactly one row in the view \n 3. hop: returns the value under the header column of the row \n 4. and: returns the boolean operation result of two arguments \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column \n 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column \n 7. argmax/argmin: returns the row with the max/min value in header column \n 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column \n 9. eq/not eq: returns if the two arguments are equal \n 10. round eq: returns if the two arguments are roughly equal under certain tolerance \n 11. greater/less: returns if argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \n 16. filter all: returns the view itself for the case of describing the whole table \n 17. all eq/not eq: returns whether all the values under the header column are equal/not equal to argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\n\neq { count { filter_eq { filter_eq { all_rows ; laps ; 334 } ; manufacturer ; chevrolet } } ; 2 } = true\n"
},
{
"from": "gpt",
"value": "select the rows whose laps record is equal to 334 . among these rows , select the rows whose manufacturer record fuzzily matches to chevrolet . the number of such rows is 2 ."
}
] |
[
{
"from": "human",
"value": "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\").\n\nExample Input: You are unable to naturally make yourself taller because height is determined by (A) parents (B) Cookies (C) Space (D) Eggshells\nExample Output: A\n\nExample Input: An example of replacing a natural resource like copper might be (A) recovering ores (B) running around (C) throwing up (D) using plastic straws\nExample Output: A\n\nExample Input: Water vapor condensing in clouds may cause (A) people to use umbrellas (B) dogs to take a nap (C) rockets to fly to the moon (D) the earth to spin\nExample Output:"
},
{
"from": "gpt",
"value": "A\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an item and you need to check whether it is edible or not, return 1 if it is edible, else return 2.\n\nmouse\n2\n\nelephant\n2\n\nteddy bear\n"
},
{
"from": "gpt",
"value": "2\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you have to generate the named entities (NER) given its ingredients of the recipe. Named entities are the names of the items without their quantity.\nQ: 1 c. margarine, 2 c. sugar, 4 eggs, 1 c. mashed bananas, 4 c. flour, 2 tsp. baking powder, 1 tsp. soda, 3/4 tsp. salt, 1 (15 1/4 oz.) can undrained crushed pineapple, 1 c. shredded coconut\nA: "
},
{
"from": "gpt",
"value": "margarine, sugar, eggs, bananas, flour, baking powder, soda, salt, pineapple, coconut"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given a dialogue between a customer and a flight booking agent with a gap in the conversation. Your job is to find the answer of the previous dialogue. Avoid using irrelevant extra information while creating the answer. The answer should be relevant to the question before the blank. If you fill the blank with a question, it should have an answer from the agent in the given dialogue. Fill the gap marked with underline.\nSee one example below:\nProblem: customer: Hello. \n agent: Hello. How may I help you? \n customer: I would like to do some changes in my existing reservation, can you please help me out? \n agent: Sure, I will help you in booking. May I know your name to proceed further? \n __ \n agent: Alexander Hernandez, regret to inform that there is no active reservation found under your name to amend. \n customer: That's ok, no problem. Thank you for the information. \n agent: Thank you for reaching us.\nSolution: customer: Sure, myself Alexander Hernandez.\nExplanation: This is pretty forward, based on the answer after the blank, the answer would be to know the name of the person, and the name is mentioned in the next dialogue to the blank\n\nProblem: customer: Hi. \n agent: Hello. How can I help you? \n __ \n agent: Please wait a moment to check the reservation status. \n customer: Sure. \n agent: Sorry, no reservation found by your name. \n customer: Not an issue. Anyway, thank you for checking. \n agent: Thanks.\nSolution:"
},
{
"from": "gpt",
"value": "customer: I am Patricia Baker. I want to stay for some more days at Minneapolis, can you please help me to change my flight reservation?"
}
] |
[
{
"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 two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\n\nSentence 1: Tim got into an argument in class. \n Sentence 3: Tim took him seriously \n Sentence 4: he told his teacher about it \n Sentence 5: The teacher intervened and got Tim's classmate in trouble \n Option 1: Tim's classmate threatened to fight him after school. \n Option 2: Tim's classmate promised to give him a cookie after school."
},
{
"from": "gpt",
"value": "Option 1"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task you are given a sentence. You must judge whether subject of the main clause is singular or plural. Label the instances as \"Singular\" or \"Plural\" based on your judgment.\nTeacher: Now, understand the problem? Solve this instance: Multiple cave openings appeared.\nStudent:"
},
{
"from": "gpt",
"value": "Plural"
}
] |
[
{
"from": "human",
"value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: Article: The atmosphere and oceans are not the only parts of the environment being damaged. Rain forests are being quickly destroyed as well, and their survival is questionable. E.O. Wilson, a biologist at Harvard, called the depletion of rain forest areas \"the greatest extinction since the end of the age of dinosaurs\". Unlike some environmental issues, rain forest depletion has fortunately received significant public and media attention. Despite the opposition to the cutting down of rain forests, the problem continues. Every year, Brazil chops down an area of forest the size of the state of Nebraska. In addition to the Amazon's rain forests, many other forests are being cut down as well. In Indonesia, Zaire, Papua-new Geinea, Malaysia, Burma, the Philippines, Peru, Colombia, Bolivia, and Venezuela, rain forests that were once great have been lost. According to some estimates, 50 million acres of rain forests are cut down every year. The United Nations says the figure is closer to 17 million acres. The World Wildlife Fund says every minute, 25 to 50 acres are cut or burned to the ground. The world's growing population has been a primary reason of rain forest destruction. More people need land to live on and wood products to consume. Limiting population growth may be the first in a series of steps that would limit the destruction of the rain forests. \n Question: In the opinion of the author, _ are being destroyed terribly at present. \n Options: (A) the rain forests (B) the oceans (C) the atmosphere (D) all the above \n Asnwer: B\nStudent:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "Q: This task is about translating a given Spanish language sentence to English.\nEstaba asombrada.\nA:"
},
{
"from": "gpt",
"value": "So I was amazed."
}
] |
[
{
"from": "human",
"value": "Given two entities as input, classify as \"yes\" if second entity is the part of the first entity. Otherwise classify them as \"no\". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity).\n\nEx Input:\nEntity 1: bike \n Entity 2: bicycle wheel\n\nEx Output:\nyes\n\n\nEx Input:\nEntity 1: network \n Entity 2: nucleus\n\nEx Output:\nno\n\n\nEx Input:\nEntity 1: pupas \n Entity 2: alkaline groundwater\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "no\n\n\n"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nIn this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. 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.\nPart 2. Example\n6, 14, ['9545', '5185', '1667', 'w', 's', '9559', 'T', 'u', 'U', '6843', 'L', 'l', '6365', '7103', 'A', '2381', '5037', 'X', '4487', 'd']\nAnswer: 9559, T, u, U, 6843, L, l, 6365, 7103\nExplanation: Here, all the elements between the 6th element and 14th element are '9559', 'T', 'u', 'U', '6843', 'L', 'l', '6365', and '7103'.\nPart 3. Exercise\n10, 22, ['e', 'V', 'F', '4927', 'l', '2525', 'm', 'y', '7545', '4739', '869', '9635', '191', '9277', '9051', 'y', 'A', 'r', '1041', 'd', '461', 'c', '9811', '3711', '6563']\nAnswer:"
},
{
"from": "gpt",
"value": "4739, 869, 9635, 191, 9277, 9051, y, A, r, 1041, d, 461, c"
}
] |
[
{
"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 pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively.\n\nSentence 1: Just off the northeast corner of the Diwan-i-Am, the harem had its very own mosque, Nagina Masjid, Hindu temple, and between the two a bazaar where merchants sold silks and jewels. Sentence 2: The vendors sold jewelry made out of gold, silver, and copper.\nOutput:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.\n\nQ: Query: where to find morel mushrooms \n Clarification: are they poisonous\n\nA: Yes\n****\nQ: Query: Tell me more on Kansas city railroad \n Clarification: are you interested in a school district\n\nA: Yes\n****\nQ: Query: I need information on income tax return online \n Clarification: do you need to apply for a federal tax return online\n\nA:"
},
{
"from": "gpt",
"value": "Yes\n****\n"
}
] |
[
{
"from": "human",
"value": "Given a passage with a question and an answer to that question, classify if the answer actually answers the question into 'yes' or 'no'. Output 'yes' if the answer answers the question and output 'no' if the answer does not answer the question.\nQ: Question: Is daily physical activity in patients with chronic obstructive pulmonary disease mainly associated with dynamic hyperinflation?\nAnswer: Daily physical activity of patients with COPD is mainly associated with dynamic hyperinflation, regardless of severity classification.\nA: "
},
{
"from": "gpt",
"value": "yes"
}
] |
[
{
"from": "human",
"value": "In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\nExample: I a am professional dancer.\nExample solution: (2,3)\nExample explanation: words 'a' and 'am' have been swapped. The correct sentence would be 'I am a professional dancer.'. Since the position of 'a' is 2 and 'am' is 3, the answer is (2,3).\n\nProblem: Three little boys eat meal a at a tiny table on a deck\n"
},
{
"from": "gpt",
"value": "Solution: (5, 6)"
}
] |
[
{
"from": "human",
"value": "Teacher:You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\nTeacher: Now, understand the problem? Solve this instance: Passage: Tammy had to do some chores for her mother . It was her turn to clean the bathroom , and cleaning the shower was one of them . She brought her cleaner with her , and a scrubber . Then she scrubbed them with the scrubber until all the dirt was gone . Then she rinsed the shower walls with the shower head . It made it easier to do , and faster . She also got down and cleaned the bathtub as well , and sometimes on her knees , she would lean down to get the spots you have to reach on your knees . Then once more , she sprayed the walls and the entire tub with the shower head again , until all the cleaner was off the walls and tub . The last thing she did was use a glass cleaner and paper towels , to use it on the glass door in the shower . Question: What did Tammy wet first? Option1: The shower walls. Option2: The glass door of the shower.\nStudent:"
},
{
"from": "gpt",
"value": "The shower walls."
}
] |
[
{
"from": "human",
"value": "Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.\n\nLet me give you an example: 03:40:40 PM doesn't occur between 5:35:38 and 07:58:59 AM\nThe answer to this example can be: False\nHere is why: The output of 'False' is correct as the input statement is false, since 03:40:40 PM occurs after 07:58:89 AM and not between 5:35:38(AM) and 07:58:59 AM\n\nOK. solve this:\n08:41:46 occurs between 02:42:03 PM and 9:01:01 PM\nAnswer:"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you need to reverse the order of words in the given sentence.\nSentence: a woman in a red snow suit skiing\nA:"
},
{
"from": "gpt",
"value": "skiing suit snow red a in woman a"
}
] |
[
{
"from": "human",
"value": "Given a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).\n\nWhat is 81/4 of a kilometer in meters?\n20250\n\nWhat is twenty-nine halves of a hour in seconds?\n52200\n\nFour letters picked without replacement from {s: 1, u: 1, v: 1, o: 2, f: 2, j: 1}. Give prob of picking 1 v, 1 u, 1 j, and 1 s.\n"
},
{
"from": "gpt",
"value": "1/70\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 are given a public comment from online platforms. You are expected to classify the comment into two classes: toxic and non-toxic. Toxicity is defiend as anything that is rude, disrespectful, or unreasonable that would make someone want to leave a converation.\n\nComment: i am just sorry that khadr didnt get a bullet in the head before he blew the head off that innocent father because his islamic boogie skywizard told him to.\nSolution: Toxic\nWhy? This is a toxic comment because it advocates acts of violence.\n\nNew input: Comment: Just shoot him now.\nSolution:"
},
{
"from": "gpt",
"value": "Toxic"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nConstruct a question that every answer in the list is correct and reasonable for it.\nPart 2. Example\numbrella, sunscreen, sun hat, sunglasses, cover up, shade\nAnswer: at the beach, name something that might protect you from sun.\nExplanation: umbrella, sunscreen, sun hat, sunglasses, cover up and shade can provide protection for the people at the beach\nPart 3. Exercise\nmiss flight, lose luggage, stopped by security, delayed\nAnswer:"
},
{
"from": "gpt",
"value": "name the last thing youd want to happen to you in the airport"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. Given a set of five words, generate the word from the set that does not belong (i.e. is the least relevant) with the other words. Words are separated by commas.\n\nwinch, crane, mallet, windlass, steam roller\n"
},
{
"from": "gpt",
"value": "mallet"
}
] |
[
{
"from": "human",
"value": "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.\n\nQ: Beginning: Eric and Paul played outside in the snow all morning. Ending: They were warmed up in no time.\n\nA: Eric and Paul came inside to sit by the fireplace.\n****\nQ: Beginning: Tim found mushrooms growing in his yard. Ending: Tim learned never to touch mysterious fungus again.\n\nA: The mushrooms made Tim sick.\n****\nQ: Beginning: Thomas is starting his first job at McDonald's Ending: He decided that he's going to start a lawn-mowing business instead.\n\nA:"
},
{
"from": "gpt",
"value": "Things didn't go well at McDonalds.\n****\n"
}
] |
[
{
"from": "human",
"value": "This task is about writing a correct answer for the reading comprehension task. Based on the information provided in a given passage, you should identify the shortest continuous text span from the passage that serves as an answer to the given question. Avoid answers that are incorrect or provides incomplete justification for the question.\nQ: Passage: Despite its tropical wet and dry climate, extensive irrigation makes it a rich agricultural region. Its canal-irrigation system established by the British is the largest in the world. Wheat and cotton are the largest crops. Other crops include rice, sugarcane, millet, corn, oilseeds, pulses, vegetables, and fruits such as kinoo. Livestock and poultry production are also important. Despite past animosities, the rural masses in Punjab's farms continue to use the Hindu calendar for planting and harvesting. Question: What are Punjab's secondary crops?\nA: "
},
{
"from": "gpt",
"value": "rice, sugarcane, millet, corn, oilseeds, pulses, vegetables, and fruits such as kinoo"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you will be presented with a question in Dutch language, and you have to write the part-of-speech tag for each word and punctuation in the question. Here is the list of part-of-speech tags used in this task: Adj: Adjective, Adv: Adverb, Art: Article, Conj: Conjunction, Int: Interjection, N: Noun, V: Verb, Num: Number, Misc: Miscellaneous, Pron: Pronoun, Prep: Preposition, Punc: Punctuation.\nInput: Vanderpoorten heeft hen die nog gegeven tot maandagnamiddag vier uur .\nOutput:"
},
{
"from": "gpt",
"value": "N V Pron Pron Adv V Prep N Num N Punc"
}
] |
[
{
"from": "human",
"value": "In this task, you're given reviews from Amazon's food products and a summary of that review. Your task is to classify whether the given summary matches the original review. Generate \"True\" if the given review and its summary match, otherwise generate \"False\".\nQ: Reviews: I wanted to recommend these because of the super cute designs but I do not recommend these at all. They feel very very thin, and they rip so easily!!!! Will not be buying these again. \n Summary: it's very red where as the photo showed a dull redish brown\nA: "
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "In this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.\nQ: Dat kan de general manager zijn tot en met de student .\nA: "
},
{
"from": "gpt",
"value": "None"
}
] |
[
{
"from": "human",
"value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou will be given two pieces of text with the same meaning. One of them is simpler and easier to understand for non-native English speakers. Complex texts may contain more difficult words, have unnecessary phrases or contain long sentences. Your task is to choose the simpler piece of text. You are expected to output 'Text one' if the first sentence is simpler. Otherwise output 'Text two'.\n\nText one: From its inception, it was designated a duty-free port and vied with the neighboring Sultanate of Pattani for trade\n Text two: From the start, it was chosen to be a duty-free port to compete with the neighboring Sultanate of Pattani for trade.\nSolution: Text two\nWhy? Text two has simpler words, ,so it is easier to understand by non-native English speakers.\n\nNew input: Text one: Some notable series that trace their look and feel to Wizardry include The Bard's Tale and Might and Magic.\n Text two: Some notable series that trace their vibe to Wizardry include The Bard's Tale and Might and Magic.\nSolution:"
},
{
"from": "gpt",
"value": "Text two"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nInput: Sentence 1: A person walks along a beach at sunset carrying a surfboard. Sentence 2: A person is walking on the beach carrying a surfboard.\nOutput:"
},
{
"from": "gpt",
"value": "The person is wearing a wetsuit."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: This task is about identifying the object of a given sentence. The object of a sentence is the person or thing that receives the action of the verb. It is the who or what that the subject does something to. Each sentence in this task is guaranteed to contain a single object. The input is a sentence and the output is the identified object of that sentence.\nProblem:The Accademia di Architettura di Mendrisio was established in 1996.\nSolution:"
},
{
"from": "gpt",
"value": "1996"
}
] |
[
{
"from": "human",
"value": "In this task, you will be shown an extract from a movie plot. You need to read the extract and create questions that can be answered from the extract. Once you create a question you also need to provide the correct answer for it. Write your answer like \"Question: your question, Answer: your answer\". The questions should be well-formed and grammatically correct. The questions should be completely answerable from the given passage and should not require any external knowledge. Subjective questions are not allowed. Short answers containing words that are present in the passage are preferred. Create questions that result in factoid answers. A simple rule of thumb to decide whether a question is a factoid or not is to see if two different people with average reading/comprehension skills would come up with the same answer after reading the passage.\n\nIn late 1945, one-armed John J. Macreedy (Spencer Tracy) gets off a passenger train at the isolated desert hamlet of Black Rock. It is the first time in four years that the train has stopped there. Macreedy is looking for a man named Komoko, but the few residents are inexplicably hostile. The young hotel desk clerk, Pete Wirth (John Ericson), claims he has no vacant rooms. Macreedy is threatened by Hector David (Lee Marvin). Later, Reno Smith (Robert Ryan) informs Macreedy that Komoko, a Japanese-American, was interned during World War II.Certain that something is wrong, Macreedy sees the local sheriff, Tim Horn (Dean Jagger), but the alcoholic lawman is clearly afraid of Smith and is impotent to help. The veterinarian and undertaker, Doc Velie (Walter Brennan), advises Macreedy to leave town immediately, but also lets slip that Komoko is dead. Pete's sister, Liz (Anne Francis), rents Macreedy a Jeep. He drives to nearby Adobe Flat, where he finds a homestead burned to the ground and wildflowers. On the way back, Coley Trimble (Ernest Borgnine) tries to run him off the road.When Smith asks, Macreedy reveals he lost his left arm fighting in Italy. Macreedy says the wildflowers at the Komoko place lead him to suspect that a body is buried there. Smith reveals that he is virulently anti-Japanese; he tried to enlist in the Marines the day after the attack on Pearl Harbor, but failed the physical.Macreedy tries to telephone the state police, but Pete refuses to put the call through. Doc Velie admits that something terrible happened four years ago and that Smith has everyone too terrified to speak up. Velie offers Macreedy his hearse to leave town. Hector rips out the distributor cap and spark plug wires. Macreedy goes to Hastings' (Russell Collins) telegraph office and writes a telegram addressed to the state police. At the town diner, Trimble picks a fight with Macreedy, but Macreedy uses martial arts to beat him up. Macreedy tells Smith that he knows Smith killed Komoko and that he was too cowardly to do it alone, so he involved Hector, Pete, and Coley.When Macreedy goes to the hotel lobby, Smith and his henchmen are already there, as are Doc Velie and Sheriff Horn. Hastings arrives and tries to give Smith a piece of paper, but Macreedy snatches it away and discovers that it is his own unsent telegram. Macreedy and Doc Velie demand that Sheriff Horn do something. When Horn tries, Smith just takes away his sheriff's badge and pins it on Hector. Hector tears up the telegram form.After Smith and Hector leave, Macreedy reveals that the loss of his arm had left him wallowing in self-pity, but Smith's attempt to kill him has reinvigorated him. Macreedy finally reveals why he is there: Komoko's son died in combat while saving Macreedy's life. Macreedy intended to give his posthumous medal to Komoko. In turn, Macreedy learns that the elder Komoko had leased some farmland from Smith, who was sure there was no water there. Komoko had dug a well and found water. After Smith was turned down for enlistment after Pearl Harbor, he and the other men spent the day drinking, then decided to scare Komoko. The old man barricaded himself inside his home, but the men set the place on fire. When Komoko emerged ablaze, Smith shot him.Later, Macreedy and Doc Velie devise a plan for Macreedy to escape under the cover of darkness. Hector is standing guard outside the hotel; Pete lures him into the hotel office, where Doc Velie knocks him out. Liz drives Macreedy out of town in her Jeep, but stops in a canyon. Macreedy realizes he has been betrayed. When Smith starts shooting at him, Macreedy hides behind the Jeep. Liz rushes to Smith despite Macreedy's warning. Smith tells her that she has to die along with the rest of his accomplices. He shoots her in the back as she runs away. Macreedy finds a bottle and fills it with gasoline, creating a Molotov cocktail. When Smith climbs down for a better shot, Macreedy lights and throws it, setting Smith on fire.Macreedy drives into town with the injured Smith and Liz's body. The state police are called in. As Macreedy is leaving, Doc Velie requests Komoko's medal to help Black Rock heal. Macreedy gives it to him just before boarding the train."
},
{
"from": "gpt",
"value": "Question: Who plays Hastings?, Answer: Russell Collins"
}
] |
[
{
"from": "human",
"value": "Teacher: In this task, you're given a context, a question, and three options. Your task is to find the correct answer to the question using the given context and options. Also, you may need to use commonsense reasoning about social situations to answer the questions. Classify your answers into 'A', 'B', and 'C'.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nContext: 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\nSolution: C\nReason: Tracy found somewhere to go and didn't come home because she wanted to resist Riley's attacks. So, C is the correct answer.\n\nNow, solve this instance: Context: Aubrey took Cameron's home and bulldozed it after winning the eminent domain case. \n Question: How would Cameron feel as a result? \n Options: (A) strong now (B) angry at being forced out of their home (C) skilled now\nStudent:"
},
{
"from": "gpt",
"value": "B"
}
] |
[
{
"from": "human",
"value": "In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. Your answer should be chosen from the given text, and should not contain other words.\n\nLet me give you an example: Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!\nThe answer to this example can be: crooler\nHere is why: In this example, the number two refers to something that the word: crooler.\n\nOK. solve this:\nCharles Aitken: Seven cities to Atlantis ? You know , the Greeks always claimed there were _ nine _ .\nAtmir: Plato was not always right .\nCharles Aitken: You know about our history ?\nAtmir: Far more than you realize .\nAnswer:"
},
{
"from": "gpt",
"value": "cities"
}
] |
[
{
"from": "human",
"value": "In 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\n[Q]: good u doing well thank you u missed megrinningfacewithbigeyesgrinningfacewithbigeyesgrinningfacewithbigeyesgrinningfacewithbigeyesgrinningfacewithbigeyesgrinningfacewithbigeyesgrinningfacewithsmilingeyesgrinningfacewithsmilingeyesgrinningfacewithsweat\n[A]: other\n\n\n[Q]: i don't knw y do u wanna knw me just for fun facewithtearsofjoyfacewithtearsofjoy\n[A]: happy\n\n\n[Q]: look at my sad life being friendzoned by a bot why did i agree to this same\n[A]:"
},
{
"from": "gpt",
"value": "sad\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For simplicity, answers should be in all lower cased letters.\nQ: Category: LEAVE 'EM LAUGHING \nClue: In an Ella Wheeler Wilcox poem, they're the 7 words that precede \"weep and you weep alone\"\nA:"
},
{
"from": "gpt",
"value": "laugh and the world laughs with you"
}
] |
[
{
"from": "human",
"value": "Instructions: In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to generate a natural language interpretation of the given command. \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view \n 2. only: returns whether there is exactly one row in the view \n 3. hop: returns the value under the header column of the row \n 4. and: returns the boolean operation result of two arguments \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column \n 6. nth max/nth min: returns the n-th max/n-th min of the values under the header column \n 7. argmax/argmin: returns the row with the max/min value in header column \n 8. nth argmax/nth argmin: returns the row with the n-th max/min value in header column \n 9. eq/not eq: returns if the two arguments are equal \n 10. round eq: returns if the two arguments are roughly equal under certain tolerance \n 11. greater/less: returns if argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \n 16. filter all: returns the view itself for the case of describing the whole table \n 17. all eq/not eq: returns whether all the values under the header column are equal/not equal to argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\nInput: eq { count { filter_eq { all_rows ; location ; usa } } ; 6 } = true\nOutput:"
},
{
"from": "gpt",
"value": "select the rows whose location record fuzzily matches to usa . the number of such rows is 6 ."
}
] |
[
{
"from": "human",
"value": "A ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.\nOne example is below.\nQ: x = 3, equation weights = [4, 2]\nA: 14\nRationale: Here, the weights represent the polynomial: 4x + 2, so we should multiply 4 by 3, and add it to 2 which results in (4*3 + 2 =) 14.\nQ: x = 8, equation weights = [9, 7]\nA:"
},
{
"from": "gpt",
"value": "79"
}
] |
[
{
"from": "human",
"value": "Part 1. Definition\nRead the given text and if it has abusive content then indicate via \"yes\". Otherwise indicate via\"no\". \nWe consider the content to be abusive if it contains any of the following instances: (1) Identity Directed Abuse (e.g., Content which contains a negative statement made against an identity. An identity is a social category that relates to a fundamental aspect of individuals community, socio-demographics, position or self-representation) (2) Affiliation Directed Abuse (e.g., Content which express negativity against an affiliation. We define affiliation as a (more or less) voluntary association with a collective. Affiliations include but are not limited to: memberships (e.g. Trade unions), party memberships (e.g. Republicans), political affiliations (e.g. Right-wing people) and occupations (e.g. Doctors).) (3) Person Directed Abuse (e.g., Content which directs negativity against an identifiable person, who is either part of the conversation thread or is named. Person-directed abuse includes serious character based attacks, such as accusing the person of lying, as well as aggression, insults and menacing language.) and (4) Counter Speech (e.g., Content which challenges, condemns or calls out the abusive language of others.). Note that URLs in the text have been replaced with [Link].\nPart 2. Example\nWas Michelangelo straight though? I mean, being a pizza-maniac ninja would indicate so, but... You never know.\nAnswer: yes\nExplanation: This text has indentity directed abuse because it is trying to judge sexual orientation of Michelangelo. Hence, the answer is \"yes\"\nPart 3. Exercise\nTotally. That mod is JUST LIKE KIM JONG-UN AND HITLER. JUST LIKE THEM.\nAnswer:"
},
{
"from": "gpt",
"value": "no"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a short article. Your job is to classify the article based on its category. Use the following classification labels, 0. World, 1. Sports, 2. Business, 3. Science or Technical. Label the text \"0\" if it contains information related to world. Label the text \"1\" if it contains information related to sports. Label the text \"2\" if it contains information related business. Label the text \"3\" if it contains science or technical related information. \n\nInput: Consider Input: Howe to be dismissed, but stays with team New York Mets Manager Art Howe has been told he will be dismissed at the end of the season, but he has agreed to remain with the team until then.\n\nOutput: 1\n\n\nInput: Consider Input: Trotter, defense step up Jeremiah Trotter got his revenge Sunday, leading an Eagles defense that pounded the Redskins - the team that released Trotter this summer.\n\nOutput: 1\n\n\nInput: Consider Input: Lockheed Martin Profit Jumps 41 in Quarter Lockheed Martin Corp. yesterday reported a 41 percent increase in profit during its third quarter as fighter jet and information technology demand continued to drive growth.\n\n"
},
{
"from": "gpt",
"value": "Output: 2\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label \"yes\" if the interpretation is appropriate for the command, otherwise generate label \"no\". \n Here are the definitions of logical operators: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nCommand: most_eq { all_rows ; venue ; amman }, interpretation: for the agg records of all rows , most of them are not equal to 0 .\nno\n\nCommand: and { only { filter_less { filter_greater { all_rows ; points ; 60 } ; tries for ; 60 } } ; eq { hop { filter_less { filter_greater { all_rows ; points ; 60 } ; tries for ; 60 } ; club } ; kidwelly rfc } }, interpretation: the average of the points record of all rows is 11 .\nno\n\nCommand: and { only { filter_eq { all_rows ; class / type ; passenger ship } } ; eq { hop { filter_eq { all_rows ; class / type ; passenger ship } ; builder } ; john roach and son } }, interpretation: select the rows whose class / type record fuzzily matches to passenger ship . there is only one such row in the table . the builder record of this unqiue row is john roach and son .\n"
},
{
"from": "gpt",
"value": "yes\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to classify the genre of the sentences from the 10 options displayed. Indicate your answer by entering the number of the choice as 1-10.\n\nEx Input:\nSentence 1: It isn't necessary to change who you are, but it would be helpful to recognize who you are. Sentence 2: Change everything about yourself and don't begin to think about who you are as a person. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\n\nEx Output:\n4\n\n\nEx Input:\nSentence 1: There is a viewing platform around the camera, allowing first-hand viewing of the cityscape; there are also helpful explanatory maps pointing out the highlights on the horizon. Sentence 2: There are no maps available. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\n\nEx Output:\n6\n\n\nEx Input:\nSentence 1: He'd had a series of victories in various types of powered vehicles, including a victory on land at Daytona Beach in Florida, before coming to Coniston in 1967 to attempt to break the world record in speed boating. Sentence 2: He attempted to break the speed boating world record in 1967 but failed. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.\n\nEx Output:\n"
},
{
"from": "gpt",
"value": "6\n\n\n"
}
] |
[
{
"from": "human",
"value": "In this task, you're given a context, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both context and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the context or linked information.\n\nContext: In 1961, the singer opened her own club, Sugar Hill: Home of the Blues Link Information: none Answer: none"
},
{
"from": "gpt",
"value": "Did Dane's club make money the year she opened it?"
}
] |
[
{
"from": "human",
"value": "Q: You will be given a piece of text either about an everyday event, or a general statement. If the event seems a plausible event to you, or the general statement makes sense matches your commonsense, output 'True', otherwise output 'False'.\nA bag is less suitable for collecting trash than a hammer.\nA:"
},
{
"from": "gpt",
"value": "False"
}
] |
[
{
"from": "human",
"value": "The input is taken from a negotiation between two participants who take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. Given an utterance and recent dialogue context containing past 3 utterances (wherever available), output Yes if the utterance contains the self-need strategy, otherwise output No. self-need is a selfish negotiation strategy. It is used to create a personal need for an item in the negotiation, such as by pointing out that the participant sweats a lot to show preference towards water packages.\nOne example is below.\nQ: Context: 'That sounds pretty reasonable as I am in need of firewood the most. Would it be most reasonable to each take what we need most and split the water down the middle?' 'Yes, it would.' 'I think that sounds fair. The problem is that there are 3 waters and one of us would get two and the other one. How should we sort that?'\nUtterance: 'You can take the two water. I am not that thirsty most days.'\nA: No\nRationale: In this utterance, the participant does not use self-need since they do not talk about any need for themselves.\nQ: Context: 'I was actually saying you get 2 firewood and I get 3 waters. Then you could have 2 food and I get 1 food.' 'That's seems fair to me since we all need food to eat' 'Okay, I'm glad we were able to work something out!'\nUtterance: 'Am also glad.You are more interested in water. Do you drink a lot of water frequently?'\nA:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.\nSee one example below:\nProblem: Sentence1:i need a place to dine in the center thats expensive Sentence2: I have several options for you; do you prefer African, Asian, or British food? Sentence3: Any sort of food would be fine, as long as it is a bit expensive. Could I get the phone number for your recommendation?Question: Who has spoken the sentence 2? (A) User (B) System\nSolution: Answer: (A) User\nExplanation: The sentence 1 is said by a user because the intent of it says that the information has to be gathered from the system\n\nProblem: Sentence1: Have a good evening. Sentence2: Bye. Sentence3: Da Vinci Pizzeria is a restaurant serving Italian food in the north part of town. Would you like any additional information? Sentence4: I am interested in a restaurant located in the north part of town that specializes in Indonesian food, please. Sentence5: what about italian food? Sentence6: The address is 20 Milton Road Chesterton and the phone number is 01223 351707. Sentence7: Goodbye. Sentence8: thank you, goodbye. Sentence9: There are no restaurants serving Indonesian food in the north part of town. Would you like me to look in another part of town? Sentence10: Yes, may I have the address and phone number please? Question: Who has spoken the sentence 2? (A) User (B) System\nSolution:"
},
{
"from": "gpt",
"value": "Answer: (A) User"
}
] |
[
{
"from": "human",
"value": "You will be given a sentence containing a pronoun/person name and an emotion. From these implicit parameters, the main goal is to find the gender of the person (male / female).\n\nCourtney found herself in a vexing situation.\nfemale\n\nThe situation makes Nichelle feel happy.\nfemale\n\nThe situation makes Heather feel sad.\n"
},
{
"from": "gpt",
"value": "female\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify this question-answer pair into two categories: (1) \"yes\" if the given answer is right for question, and (2) \"no\" if the given answer is wrong for question.\n\nContext: RealGM @RealGMCarmelo Anthony Will Consider Leaving If Knicks Prefer Trade: , 6:54:34 PM Question: why is he wanting to leave Answer: more money advance his career\n"
},
{
"from": "gpt",
"value": "yes"
}
] |
[
{
"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: A *** in a *** *** is called the (A) producer. (B) consumer. (C) decomposer. (D) energizer."
},
{
"from": "gpt",
"value": "E."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you're given a four sentences of story written in natural language. Your job is to complete end part of the story by predicting appropriate last sentence which is coherent with the given sentences.\nProblem:Sentence1: Monica was taking her daughter to see Santa at the mall. Sentence2: The line was insanely long. Sentence3: Monica didn't want to wait but knew her daughter would be upset. Sentence4: Finally she decided to just suck it up and wait.\nSolution:"
},
{
"from": "gpt",
"value": "They actually made it through the line quicker than expected."
}
] |
[
{
"from": "human",
"value": "In this task, you're given a short story of five sentences written in natural language. However, the order of the given story is not correct. Your job is to return the correct order for the given five sentences to create a coherent short story with the new order that has the correct flow. Generate your answer using the number of sentences in the correct order, such as '23415'.\n\n[Q]: Sentence1: He finally quit after 6 months. Sentence2: Ron was proud of the decision he made. Sentence3: Ron decided it was best if he didn't drink anymore. Sentence4: Ron liked to drink a lot of beer. Sentence5: His dad and his mom were both alcoholics.\n[A]: 45312\n\n\n[Q]: Sentence1: Tori received a call from the bank regarding charges on her ATM card. Sentence2: She called Anne and told her that someone had been using her card. Sentence3: They often shopped together. Sentence4: Ann and Tori had been friends for over 20 years. Sentence5: Ann and Tori decided to stop shopping and work out the issue.\n[A]: 34215\n\n\n[Q]: Sentence1: It made him sick to his stomach. Sentence2: Marcus then vomited from sea sickness. Sentence3: The sea was frightening during a storm. Sentence4: He cowered in his cabin and shut his eyes but it didn't help. Sentence5: Marcus hated the way the boat rose up and crashed down.\n[A]:"
},
{
"from": "gpt",
"value": "35142\n\n\n"
}
] |
[
{
"from": "human",
"value": "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.\n\nLet me give you an example: Article: Homework can put you in a badmood , and that might actually be a good thing. Researchers from the University of Plymouth in England doubted whether mood might affect the way kids learn. To find out the answer, they did two experiments with children. The first experiment tested 30 kids. Someshapes were hidden inside a different, larger picture. The kids had to find the small shapes while sitting in a room with either cheerful or sad music playing in the background. To test their mood, the scientists asked the kids to point to one of five faces, from happy to sad. Children who listened to cheerful music tended to point to the smiley faces while the others pointed to the unhappy ones. The researchers found that sad kids took at least a second less to find the small shapes. They also found an average of three or four more shapes. In the second experiment, 61 children watched one of two scenes from a film. One scene was happy, and the other was sad. Just like in the first experiment, kids who saw the sad scene acted better compared to the others. The researchers guessed that feeling down makes people more likely to focus on a problem or difficult situation. Not all scientists agree with them, however. Other studies argued that maybe, that cheerful music in the first experiment distracted kids from finding shapes. While scientists work on finding out the answers, it still might be wise to choose when to do your tasks according to your mood. After eating a delicious ice cream, for example, write an essay. \n Question: Researchers did experiments on kids in order to find out _ . \n Options: (A) how they really feel when they are learning (B) whether mood affects their learning ability (C) what methods are easy for kids to learn (D) the relationship between sadness and happiness \n Answer: B\nThe answer to this example can be: Yes\nHere is why: It is clearly mentioned in the article that to the check effect of mood on children is the main purpose of the experiment. Hence, B is the correct answer and output is Yes.\n\nOK. solve this:\nArticle: Older fathers have uglier children, researchers have claimed after linking age to genetic mutations . The finding comes weeks after leading scientists reported children born to men over the age of 45 run a higher risk of having autism and mental disorders. With age, sperm -producing cells do not copy a man's DNA as effectively, leading to genetic mutations. Martin Fielder, an anthropologist at Vienna University, told the Sunday Times: 'Every 16 years the mutation rate doubles. Other researchers found 25 mutations per sperm in a 20-year-old, but at age 40 it is 65 mutations. By 56, it doubles again. The effect is very visible - someone born to a father of 22 is already 5-10 per cent more attractive than those with a 40-year-old father and the difference grows with the age gap. In contrast, women pass on a maximum of 15 mutations to their baby, regardless of age, according to the study published in the journal Nature. Surveying a group of six men and six women, researchers showed them each 4,018 photographs of 18-20-year-old men and 4,416 of women the same age, and asked to assess their attractiveness. Those with older fathers were consistently considered less attractive. However, the children of older men, though less attractive, are likely to outlive their peers with younger fathers, it is claimed. Professor Lee Smith, a geneticist at Edinburgh University, told the Sunday Times other research found such children have longer telomeres - the caps on the end of chromosomes --- which are associated with longer life. But the mounting research connecting parents' age with autism is cause for concern, experts warn. Autism is an umbrella term for a range of developmental disorders that have a lifelong effect on someone's ability to interact socially and communicate openly. In the UK, around one in 100 adults is thought to be affected by autism, mostly men, caused by a combination of genetic and environmental factors. Researchers said men should be advised about the potential problems in order to help their personal decision-making when it came to having fathering children at older ages. They warned that advancing paternal age faced a risk of 'numerous public health and societal problems'. Among well-known older dads are Simon Cowell, 54, whose son was born earlier this month, and comedian Frank Skinner whose first child was born in 2012 when he was 55. \n Question: From the passage, we know that _ . \n Options: (A) Genetic mutations are caused by old age and physical disorders (B) When a man becomes older, sperm-producing cells copy his DNA less effectively (C) One of the advantages older fathers have is that their children can live a longer life (D) Researchers advise men to avoid having fathering children at older ages. \n Asnwer: D\nAnswer:"
},
{
"from": "gpt",
"value": "No"
}
] |
[
{
"from": "human",
"value": "In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.\n\n[Q]: ['a', 'i', '7725', '2483', 'e', 'j', '5337', 'b', '6835', '8231', 'm', 'v', 'a', '1475', 'n', '5823', 's', 'm', '7313', '2841', '2585', '4673', 'u', '2083', 'z', 'd', 'p', '2117', 'i', '587', 'i', 'a', '2527', '7967', '6567', 'n', '6145', 'r', 'f']\n[A]: a, b, d, e, f, i, j, m, n, p, r, s, u, v, z\n\n\n[Q]: ['4009', 'y', '9077', 'p', 'q', '6711', '6443', '5491']\n[A]: p, q, y\n\n\n[Q]: ['6437', '2739', '8419']\n[A]:"
},
{
"from": "gpt",
"value": "-1\n\n\n"
}
] |
[
{
"from": "human",
"value": "Teacher:In this task, you need to reverse the order of words in the given sentence.\nTeacher: Now, understand the problem? Solve this instance: Sentence: the view of a shoreline with a long grass park\nStudent:"
},
{
"from": "gpt",
"value": "park grass long a with shoreline a of view the"
}
] |
[
{
"from": "human",
"value": "Definition: Given an English language product review, determine if it is a Good Review or a Bad Review. A good review is one where the product's review has positive tone and Bad review is one where the tone of product's review is negative.\nInput: Works well in conjunction with Dr.\nOutput:"
},
{
"from": "gpt",
"value": "Good Review"
}
] |
[
{
"from": "human",
"value": "Definition: In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\nInput: ['4253', 'P', 'B', '6657', 'd', '7085', 'k', '2853', 'Y']\nOutput:"
},
{
"from": "gpt",
"value": "P, B, d, k, Y"
}
] |
[
{
"from": "human",
"value": "Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\nOne example: Jacob entered the dining_room. William entered the dining_room. The tomato is in the green_drawer. William exited the dining_room. Jacob moved the tomato to the blue_cupboard. Jacob is in the dining_room. Olivia entered the dining_room. The cucumber is in the blue_cupboard. Olivia exited the dining_room. Jacob moved the cucumber to the green_drawer. William entered the pantry. Jacob entered the pantry. The asparagus is in the red_cupboard. Jacob exited the pantry. William moved the asparagus to the green_pantry. Abigail entered the hall. William entered the hall. The persimmon is in the blue_pantry. William exited the hall. Abigail moved the persimmon to the blue_envelope. Where does Abigail think that William searches for the persimmon?\nSolution is here: blue_pantry\nExplanation: The persimmon was last in the blue_pantry before William exited the hall. After William exited the hall, Abigail moved the persimmon to the blue_envelope, so she knows where William will look for it.\n\nNow, solve this: Oliver entered the cellar. Sophia entered the cellar. The pineapple is in the blue_container. Sophia exited the cellar. Oliver moved the pineapple to the blue_suitcase. Where was the pineapple at the beginning? Sophia entered the cellar. Aiden entered the cellar. The strawberry is in the blue_suitcase. Sophia moved the strawberry to the blue_container. Where does Sophia think that Aiden searches for the strawberry?\nSolution:"
},
{
"from": "gpt",
"value": "blue_container"
}
] |
[
{
"from": "human",
"value": "You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.\n\npassword = xAN841Smvm8K0BxCno9D3BBYfq"
},
{
"from": "gpt",
"value": "6"
}
] |
[
{
"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 string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\n\nthreesevenfourthreefour\nOutput:"
},
{
"from": "gpt",
"value": "37434"
}
] |
[
{
"from": "human",
"value": "Definition: You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No.\nInput: Sentence: In 2006 UNESCO declared these seven groups of monuments as a World Heritage Site (WHS). \nQuestion: When did the Kathmandu valley monuments receive WHS status?\nOutput:"
},
{
"from": "gpt",
"value": "Yes."
}
] |
[
{
"from": "human",
"value": "Given two entities as input, classify as \"yes\" if second entity is the part of the first entity. Otherwise classify them as \"no\". These are entities of meronym In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., second entity) is in a part-of relationship with its holonym (i.e., first entity).\n--------\nQuestion: Entity 1: steroid \n Entity 2: dopamine\n\nAnswer: no\n\n\nQuestion: Entity 1: network \n Entity 2: nucleus\n\nAnswer: no\n\n\nQuestion: Entity 1: cheetah \n Entity 2: nectar\n\nAnswer:"
},
{
"from": "gpt",
"value": "no\n\n\n"
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In medical studies, treatments are tested within a group of study participants. You will be given a sentence of a study report in which your task is to list the phrases that give information about the participants of the study. You should list the phrases in the same order that they appear in the text, separated by commas. If no information about the participants is mentioned, just output \"not found\". Relevant information about participants include: gender, medical conditions, location, number of people participating. Do not contain participant mentions without relevant information.\nQ: Social skills improvement in children with high-functioning autism : a pilot randomized controlled trial .\nA:"
},
{
"from": "gpt",
"value": "children with high-functioning autism"
}
] |
[
{
"from": "human",
"value": "Q: In this task, you're given two sentences. Indicate if the first sentence clearly entails the second sentence (i.e., one can conclude the 2nd sentence by reading the 1st one). Indicate your answer with '1' if the first sentence entails the second sentence, otherwise answer with '0'.\nSentence 1: A Miami International Airport concourse was evacuated for three hours Wednesday, after a pepper spray can discharged, causing 43 people to suffer respiratory distress. Sentence 2: An Airport concourse was evacuated Wednesday, after people began having trouble breathing.\nA:"
},
{
"from": "gpt",
"value": "1"
}
] |
[
{
"from": "human",
"value": "TASK DEFINITION: In this task, you need to replace a letter in the sentence with another given letter.\nPROBLEM: Sentence: 'a red stop sign sitting on the side of a road'. Replace the letter 'r' with 'o' in the sentence.\n\nSOLUTION: a oed stop sign sitting on the side of a ooad\n\nPROBLEM: Sentence: 'three colorful knit bear toys with button eyes'. Replace the letter 'r' with 'z' in the sentence.\n\nSOLUTION: thzee colozful knit beaz toys with button eyes\n\nPROBLEM: Sentence: 'a new baby elephant that is staying very close to mom'. Replace the letter 'a' with 'q' in the sentence.\n\nSOLUTION:"
},
{
"from": "gpt",
"value": "q new bqby elephqnt thqt is stqying very close to mom\n\n"
}
] |
[
{
"from": "human",
"value": "Given the task definition, example input & output, solve the new input case.\nGiven a sentence, generate a most unlikely next statement. The next statement should not be logically relevant to the given context\nExample: The girls continue to speak with one another while the girl knits. They\nOutput: put the bars around while speaking and play.\nThis is incorrect as the girls are not playing, they are knitting.\n\nNew input case for you: Women walks to a a barn. people start playing beerpong in a party and a lot of people\nOutput:"
},
{
"from": "gpt",
"value": "are taking boxing boxing gloves."
}
] |
[
{
"from": "human",
"value": "Detailed Instructions: In this task, you have to generate the named entities (NER) given its ingredients of the recipe. Named entities are the names of the items without their quantity.\nQ: 6 plum tomatoes, quartered lengthwise, coarse sea salt, to taste, 1 12 cups french green lentils, 3 tablespoons extra virgin olive oil, 1 yellow onion, minced, 1 carrot, peeled and minced, 1 celery, minced, 6 cups rich vegetable stock, 1 lb red new potato, unpeeled, quartered, 1 tablespoon minced fresh rosemary, salt and pepper, to taste\nA:"
},
{
"from": "gpt",
"value": "tomatoes, salt, extra virgin olive oil, yellow onion, carrot, celery, vegetable stock, red new potato, fresh rosemary, salt"
}
] |
[
{
"from": "human",
"value": "Given the task definition and input, reply with output. In this task, you're given passages that contain mentions of names of people, places, or things. Some of these mentions refer to the same person, place, or thing. Your job is to write questions that evaluate one's understanding of such references. Good questions are expected to link pronouns (she, her, him, his, their, etc.) or other mentions to people, places, or things to which they may refer. Do not ask questions that can be answered correctly without understanding the paragraph or having multiple answers. Avoid questions that do not link phrases referring to the same entity. For each of your questions, the answer should be one or more phrases in the paragraph, and it should be unambiguous.\n\nPassage: Hunter gatherers settled the territory in the stone and iron ages, followed later by Bantu peoples. The population coalesced first into clans and then into kingdoms. The Kingdom of Rwanda dominated from the mid-eighteenth century, with the Tutsi kings conquering others militarily, centralising power and later enacting anti-Hutu policies. Germany colonised Rwanda in 1884 as part of German East Africa, followed by Belgium, which invaded in 1916 during World War I. Both European nations ruled through the kings and perpetuated a pro-Tutsi policy. The Hutu population revolted in 1959. They massacred numerous Tutsi and ultimately established an independent, Hutu-dominated state in 1962. A 1973 military coup saw a change of leadership, but pro-Hutu policy remained. The Tutsi-led Rwandan Patriotic Front launched a civil war in 1990. The presidents of Rwanda and Burundi, both Hutus, died together when their plane was shot down in April 1994. Social tensions erupted in the 1994 genocide, in which Hutu extremists killed an estimated 500,000 to 1 million Tutsi and moderate Hutu. The RPF ended the genocide with a military victory.\nRwanda's economy suffered heavily in wake of the 1994 genocide, but has since strengthened. The economy is based mostly on subsistence agriculture. Coffee and tea are the major cash crops for export. Tourism is a fast-growing sector and is now the country's leading foreign exchange earner. Rwanda is one of only two countries in which mountain gorillas can be visited safely, and visitors pay high prices for gorilla tracking permits. Music and dance are an integral part of Rwandan culture, particularly drums and the highly choreographed intore dance. Traditional arts and crafts are produced throughout the country, including imigongo, a unique cow dung art.\n"
},
{
"from": "gpt",
"value": "What country did Belgium invade in 1916?"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.