Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "In this task, you need to provide the correct option for a given problem from the provided options.\n\n[Q]: Problem: the ratio of number of boys and girls in a school is 2 : 5 . if there are 420 students in the school , find the number of girls in the school ? \nOptions: a ) 150 , b ) 250 , c ) 300 , d ) 370 , e ) 280\n[A]: c\n\n\n[Q]: Problem: in a colony of 50 residents , the ratio of the number of men and women is 3 : 2 . among the women , the ratio of the educated to the uneducated is 1 : 3 . if the ratio of the number of education to uneducated persons is 4 : 6 , then find the ratio of the number of educated and uneducated men in the colony ? \nOptions: a ) 1 : 1 , b ) 3 : 2 , c ) 1 : 3 , d ) 2 : 5 , e ) 5 : 7\n[A]: a\n\n\n[Q]: Problem: two numbers are in the ratio 3 : 4 . if their l . c . m . is 60 . what is sum of the numbers ? \nOptions: a ) 35 , b ) 56 , c ) 76 , d ) 84 , e ) 85\n[A]:" }, { "from": "gpt", "value": "a\n\n\n" } ]
[ { "from": "human", "value": "You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.\nQ: System Reference: there is a hotel called in the wharf inn and in the area of fishermans wharf.\nOriginal Reference: the wharf inn is in fishermans wharf.\nA: " }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nThe input is a conversation between an automated system and a user looking for suggestions for pubs, restaurants and coffee shops in Cambridge. In the dialogue, the user may provide some criteria for the type of place they want such as price range, cuisine, etc. Similarly, the user may ask details of the place suggested by the system such as phone number, address, etc. Given such a dialogue, output a summary of the dialogue stating the criteria provided and details seeked by the user in this dialogue. The summary should strictly be in second person point of view. The summary should not contain any information that was not present in the conversation.\nExample: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'im looking for an expensive restaurant and it should be in the addenbrookes area'\nSystem: 'Are you looking for somewhere near a particular venue? For example, Sidney Sussex College, Williams Art and Antiques, or Primavera.'\nUser: 'i dont care'\nSystem: 'The Lucky Star is an outstanding restaurant, it's in the Addenbrooke's part of town and it's in the expensive price range.'\nUser: 'whats the address'\nSystem: 'The Lucky Star is on Unit.'\nUser: 'what type of food'\nSystem: 'The Lucky Star serves chinese food.'\nUser: 'thank you good bye'\n\nOutput: You want to find an expensive restaurant and it should be in the Addenbrookes area. You want to know the address and type of food of the venue.\nThe sentence is in the second person point of you and lists the criteria provided and details seeked by the user in the conversation.\n\nNew input case for you: System: 'Thank you for calling the Cambridge Information system. Your call will be recorded for research purposes. You may ask for information about a place to eat, such as a restaurant, a pub, or a cafe. How may I help you?'\nUser: 'im looking for a moderately priced restaurant and it should be in the kings hedges area'\nSystem: 'What part of town do you have in mind? For example, something in the Addenbrooke's, Castle Hill, or King's Hedges area.'\nUser: 'it should be the in the kings hedges area'\nSystem: 'The Ranch, which is in the King's Hedges part of town, is an outstanding restaurant. It's in the moderate price range.'\nUser: 'i need the address phone number and the postcode'\nSystem: 'The Ranch, which is in the area with the postcode CB4 3JP, is located on 100 Histon Road. Its phone number is 01223322772.'\nUser: 'thank you goodbye'\n\nOutput:" }, { "from": "gpt", "value": "You are looking for a moderately priced restaurant and it should be in the Kings Hedges area. You want to know the address, phone number, and postcode of the venue." } ]
[ { "from": "human", "value": "In this task you are given data in the tabular format and a question. Write the answer to the question based on the information in the table.\n\nQ: Table: ['Location', 'Town', 'Output (MW AC)', 'Modules', 'Number of arrays']. ['H. Lee Dennison Building', 'Hauppauge', '1.75', '7,737', '24']. ['North County Complex', 'Hauppauge', '0.5', '3,431', '9']. ['Cohalan Court Complex', 'Central Islip', '3.5', '15,113', '27']. ['Riverhead County Center', 'Riverside', '3', '11,536', '31']. ['Brentwood LIRR Parking Lot', 'Brentwood', '1', '3,924', '11']. ['Deer Park LIRR Parking Lot', 'Deer Park', '2.25', '3,924', '39']. ['Ronkonkoma LIRR Parking Lot (south)', 'Ronkonkoma', '5', '20,110', '44']. Question: which towns had less than 20 arrays?\n\nA: ['Hauppauge', 'Brentwood']\n***\nQ: Table: ['Pos', 'No', 'Driver', 'Team', 'Laps', 'Time/Retired', 'Grid', 'Points']. ['1', '14', 'Robert Doornbos', 'Minardi Team USA', '107', '1:45:07.617', '15', '31']. ['2', '21', 'Neel Jani', 'PKV Racing', '107', '+6.1 secs', '5', '27']. ['3', '3', 'Oriol Servia', 'Forsythe Racing', '107', '+6.9 secs', '4', '26']. ['4', '5', 'Will Power', 'Team Australia', '107', '+7.5 secs', '12', '23']. ['5', '1', 'Sebastien Bourdais', 'N/H/L Racing', '107', '+8.0 secs', '2', '21']. ['6', '2', 'Graham Rahal', 'N/H/L Racing', '107', '+9.6 secs', '6', '19']. ['7', '19', 'Bruno Junqueira', 'Dale Coyne Racing', '107', '+14.0 secs', '10', '17']. ['8', '22', 'Tristan Gommendy', 'PKV Racing', '107', '+19.2 secs', '8', '15']. ['9', '42', 'Jan Heylen', 'Conquest Racing', '107', '+28.5 secs', '13', '13']. ['10', '15', 'Simon Pagenaud', 'Team Australia', '107', '+48.4 secs', '9', '11']. ['11', '3', 'Paul Tracy', 'Forsythe Championship Racing', '105', '+ 2 Laps', '11', '10']. ['12', '28', 'Mario Dominguez', 'Pacific Coast Motorsports', '104', '+ 3 Laps', '14', '12']. ['13', '22', 'Justin Wilson', 'RSPORTS', '87', '+ 20 Laps', '1', '8']. ['14', '29', 'Alex Figge', 'Pacific Coast Motorsports', '34', 'Contact', '0', '7']. ['15', '11', 'Alex Tagliani', 'RSPORTS', '83', 'Mechanical', '8', '6']. ['16', '11', 'Katherine Legge', 'Dale Coyne Racing', '13', 'Contact', '16', '5']. ['17', '4', 'Dan Clarke', 'Minardi Team USA', '3', 'Contact', '3', '4']. Question: who are all the drivers?\n\nA: ['Robert Doornbos', 'Neel Jani', 'Oriol Servia', 'Will Power', 'Sebastien Bourdais', 'Graham Rahal', 'Bruno Junqueira', 'Tristan Gommendy', 'Jan Heylen', 'Simon Pagenaud', 'Paul Tracy', 'Mario Dominguez', 'Justin Wilson', 'Alex Figge', 'Alex Tagliani', 'Katherine Legge', 'Dan Clarke']\n**\nQ: Table: ['Name', 'Animal Type', 'Introduced', 'Reintroduced', 'Retired', 'Beanie Baby Resembled']. ['Antlers', 'Moose', '', '1999 (neon)', '1999', 'Chocolate']. ['Baba', 'Lamb', '', '1999 (neon)', '1999', 'Fleece']. ['Bruiser', 'Bulldog', '1997', '', '', 'Wrinkles']. ['Carrots', 'Bunny', '', '1999 (neon)', '1999', 'Ears, but pink instead of brown']. ['Chewy', '', '', '1999 (neon)', '1999', '']. ['Clover', 'Bunny', '1998', '', '', 'Ears, but white instead of brown']. ['Foxy', 'Fox', '', '', '', 'Sly']. ['Glide', 'Porpoise', '', '', '', 'Echo the Dolphin']. ['Huggy', 'Bear', '1995', '1999 (neon)', '1999', 'Cubbie, but yellow instead of brown']. ['Meow', 'Cat', '1997', '1999 (neon)', '1999', 'Snip']. ['Moo', 'Cow', '1995', '', '', 'Daisy, but with white body instead of black']. ['Oink', 'Pig', '1995', '', '', 'Squealer']. ['Paddles', 'Platypus', '', '1999 (neon)', '1999', 'Patti']. ['Purr', 'Tiger', '', '', '', 'Stripes, but yellow-orange instead of orange-black']. ['Red', 'Bull', '', '', '', 'Snort']. ['Ribbit (All-Green)', 'Frog', '1995', '1999 (neon)', '1999', 'Legs']. ['Ribbit (Green-Yellow)', 'Frog', '', '', '', 'Smoochy']. ['Sherbert', 'Tie-Dye Bear', '1998', '1999 (neon)', '1999', 'Sammy']. ['Snap (All-Yellow)', 'Turtle', '1995', '', '', 'Speedy, but yellow instead of green']. ['Snap (Yellow-Green)', 'Turtle', '', '1999 (neon)', '', 'Peekaboo']. ['Snuggy', 'Bear', '1995', '', '', 'Cubbie, but pink instead of brown']. ['Sparkler', 'Bear', '', '', '1999', 'Spangle']. ['Speckles', 'Leopard', '', '', '', 'Freckles']. ['Spotty', 'Dalmatian', '', '', '', 'Dotty']. ['Squirt', 'Elephant', '', '1999 (neon)', '1999', 'Peanut']. ['Swinger', 'Monkey', '', '1999 (neon)', '1999', 'Bongo']. ['Tide', 'Whale', '', '', '', 'Splash']. ['Tubby', 'Hippopotamus', '', '', '', 'Happy']. ['Woof', 'Dog', '1995', '1999 (neon)', '1999', 'Bones']. ['Zulu', 'Zebra', '', '', '', 'Ziggy, but pink-green instead of black-white']. Question: what are the types of pillow pal animals?\n\nA:" }, { "from": "gpt", "value": "['Antlers', 'Moose', 'Lamb', 'Bulldog', 'Bunny', '', 'Bunny', 'Fox', 'Porpoise', 'Bear', 'Cat', 'Cow', 'Pig', 'Platypus', 'Tiger', 'Bull', 'Frog', 'Frog', 'Tie-Dye Bear', 'Turtle', 'Turtle', 'Bear', 'Bear', 'Leopard', 'Dalmatian', 'Elephant', 'Monkey', 'Whale', 'Hippopotamus', 'Dog', 'Zebra']\n**\n" } ]
[ { "from": "human", "value": "Q: You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language.\nBacon_sandwich \| country \| United_Kingdom\nA:" }, { "from": "gpt", "value": "Bacon sandwich is a dish from the United Kingdom." } ]
[ { "from": "human", "value": "In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n\| Attribute \| triggerword \| contrastive triggerword \| \n\| age \| old \| new \| \n\| altitude \| low \| high \|\n\| area \| small \| vast \| \n\| brightness \| dark \| light \| \n\| clarity \| obscure \| clear \| \n\| cleanness \| dirty \| clean \| \n\| complexity \| simple \| complex \| \n\| cost \| cheap \| expensive \|\n\| density \| sparse \| dense \|\n\| depth \| shallow \| deep \|\n\| distance \| near \| far \| \n\| electric conductivity \| low \| high \|\n\| flexibility \| rigid \| flexible \|\n\| granularity \| fine \| coarse \| \n\| hardness \| soft \| hard \| \n\| length \| short \| long \| \n\| magnitude \| small \| large \| \n\| mass \| small \| large \| \n\| odor \| weak \| strong \| \n\| pressure \| low \| high \| \n\| resistance \| low \| high \| \n\| shape \| round \| sharp \|\n\| shape \| flat \| spiky \|\n\| size \| small \| large \| \n\| sound \| quiet \| loud \| \n\| sound pitch \| low \| high \| \n\| speed \| slow \| fast \| \n\| stability \| unstable \| stable \| \n\| strength \| weak \| strong \| \n\| temperature \| low \| high \| \n\| texture \| smooth \| rough \| \n\| thermal conductivity \| low \| high \|\n\| thickness \| thin \| thick \| \n\| volume \| small \| large \|\n\| weight \| light \| heavy \| \n\| width \| narrow \| wide \| \n\| location \| in \| out \|\n\| location \| up \| down \|\n\| location \| above \| below \|\n\| location \| on \| off \|\n\| location \| to \| from \|\n\nQ: Context Word: eyes. \nQuestion: For Beth, applying eyeliner to her eyes was more difficult than applying lipstick to her lips because using the _ was more difficult to have a perfect application. \nAnswer: eyeliner.\nA: " }, { "from": "gpt", "value": "For Beth, applying eyeliner to her eyes was more difficult than applying lipstick to her lips because using the _ was less difficult to have a perfect application." } ]
[ { "from": "human", "value": "Q: In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.\nThe vast majority of people in this country are keeping their (health insurance) plan.\nA:" }, { "from": "gpt", "value": "health-care" } ]
[ { "from": "human", "value": "Definition: In this task, you're given four sentences of a story written in natural language in which one part is missing. Your job is to predict the position and missing part of the story and return in the following format: position, missing part. The missing part is a sentence that completes the story, and the position is the number of the missing sentence in the new story.\nInput: Sentence1: I bought a car a few months ago. Sentence2: I did a few changes and had friends help with others. Sentence3: Unfortunately it no longer passed my state's inspection. Sentence4: I had to sell the car in another state.\nOutput:" }, { "from": "gpt", "value": "2, I thought I would make it cooler by modifying it." } ]
[ { "from": "human", "value": "Part 1. Definition\nGiven a scientific question, generate an incorrect answer to the given question. The incorrect answer should be a plausible alternative to the correct answer. The answer should be some other item belonging to the same category as the correct answer but should be incorrect.\nPart 2. Example\nWhat are arteries, veins, and capillaries examples of?\nAnswer: tissue\nExplanation: Blood vessels include arteries, veins, and capillaries. Tissue is a combination of cells.\nPart 3. Exercise\nWhat material is regularly used in human hip and knee implants?\nAnswer:" }, { "from": "gpt", "value": "wood" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the numerical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no numerical element is in the list.\nTeacher: Now, understand the problem? Solve this instance: ['t', 'S', '7231', 'V', 'F', 'l', '8905', 'S', 'q', '2045', '5821', 'k', 'V', 'Y', 'l', '6349', 'f', 'A', 'i', '8201', 'E', 'Q', '8157', 'N', '6927', '3287', '8847', 'u', 'Q']\nStudent:" }, { "from": "gpt", "value": "3, 7, 10, 11, 16, 20, 23, 25, 26, 27" } ]
[ { "from": "human", "value": "Definition: Write an incorrect answer to the given question based on the associated fact. You are also provided with the correct answer to the given question. Make sure that your incorrect answer is relevant and similar to the associated fact. Also, try to make the incorrect answer similar to the correct answer so that distinguishing the correct answer from the incorrect answer is not very easy. Make sure you don't accidentally provide another correct answer! Also, make sure they sound reasonable (e.g., might be on a school pop quiz). A good incorrect answer can be constructed using words associated with the question, but not the correct answer. For example, for the question \"What helps plants survive?\", using words like \"weeds\", \"vase\", \"bee\" (associated with \"plant\"), or \"first aid\", \"parachute\", \"accident\" (associated with \"survive\") etc. Your incorrect answers make the question hard, so these results in good incorrect answers.\nInput: Fact: Blood type is important in case of an acute stroke. \nQuestion: What is important in case of acute stroke? \nCorrect Answer: blood type.\nOutput:" }, { "from": "gpt", "value": "calling the veterinarian." } ]
[ { "from": "human", "value": "Teacher: 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nContext: During Operation Market Garden, the attempt to seize a bridgehead across the Rhine in the Netherlands, the 704th dropped supplies to allied troops near Nijmegen. Link Information: Operation Market Garden was a failed World War II military operation fought in the Netherlands from 17 to 25 September 1944. Answer: from 17 to 25 September 1944\nSolution: When did the operation during which the 704th dropped supplies to allied troops near Nijmegen begin?\nReason: The context describes the 704th's actions during Operation Market Garden, and the answer specifies when the operation happened.\n\nNow, solve this instance: Context: they qualified for her second Scotties Tournament of Hearts by going undefeated at the 2013 Ontario Scotties Tournament of Hearts. Link Information: The 2013 Ontario Scotties Tournament of Hearts, women's provincial curling championship, was held January 21-27, 2013 at the Kitchener-Waterloo Granite Club in Waterloo, Ontario. Answer: Waterloo\nStudent:" }, { "from": "gpt", "value": "In which city was Miskew's team undefeated and qualified for her second Scotties Tournament of Hearts?" } ]
[ { "from": "human", "value": "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.\n\nInput: Consider Input: ['2921', '883', '4139', '5193', 'p', 'Q', 'S', '4613', 'Z', 'e']\n\nOutput: p, Q, S, Z, e\n\n\nInput: Consider Input: ['F', '835', '3873', 'N', 'W', 'C', '2215', 'i', '3789', '425', '9577', '8153', '4823', '7393', '2569', '6705', 'f', '1493', 'S', '6749', '2169', 'd', 'y', '4161', '6987', 'z', '1013', '8161', 'S', '5969']\n\nOutput: F, N, W, C, i, f, S, d, y, z, S\n\n\nInput: Consider Input: ['S', 'Z', 'F', 'z', 't', 'K', 'r', 'q', 'L', '1919', 'G', '7625', '2271', 'w', '1111', 'F', 'G', 'B', '7027', '2423', '9761', 't', 'e', '3997', '1977']\n\n" }, { "from": "gpt", "value": "Output: S, Z, F, z, t, K, r, q, L, G, w, F, G, B, t, e\n\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: Given a scientific question, generate a correct answer to it.\nPROBLEM: What are ionic solutes?\n\nSOLUTION: electrolytes\n\nPROBLEM: The average number of individuals per unit of area can be expressed as what?\n\nSOLUTION: population density\n\nPROBLEM: What is a measure that has both size and direction?\n\nSOLUTION:" }, { "from": "gpt", "value": "vector\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you're given a review from Amazon and category of the product based on the review given by the user and your task is classify whether the given category match the review. Generate \"True\" if given review and its category match, otherwise generate \"False\".\nInput: Reviews: Aside from the fact the device should come with a sleep timer already built in, the timer app would pause as soon as I switched to the video app. After several attempts at trying to figure out how to use it, (no instructions included) got it to work on a 5 minute setting-- it simply froze the video on the screen. Rate it a 0 if possible. I like to watch movies in bed at night and more often than not, fall asleep before it's over. Looked everywhere for a solution to save battery and this was only option I could find. That said, it's absolutely useless for my needs. May work well for music on android phones. \n Category: drugstore\nOutput:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Teacher:In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\nTeacher: Now, understand the problem? Solve this instance: Sentence1: 'a knife on a handcrafted wooden cutting board', Sentence2: 'a red train that is on a rail road track'. Is the frequency of the word 'handcrafted' in two sentences equal?\nStudent:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.\nExample: bYubMFxyTqR, AcDbMFxSnI\nExample solution: bYubfmxyTqR, AcDbfmxSnI\nExample explanation: Here, 'bMFx' is the longest common substring in both the input strings 'bYubMFxyTqR' and 'AcDbMFxSnI'. Sorting it and converting to lowercase gives 'bfmx'. Replacing 'bfmx' instead of 'bMFx' in the two strings gives 'bYubfmxyTqR' and 'AcDbfmxSnI'\n\nProblem: jcRUkgYhVpKlDAFYRoErvwnPCTkMpjBghHIxPVFMtUK, VbiWRaDZIyxRoErvwnPCTkMpjBgiQntMcOsLUsanvs\n" }, { "from": "gpt", "value": "Solution: jcRUkgYhVpKlDAFYbcegjkmnopprrtvwhHIxPVFMtUK, VbiWRaDZIyxbcegjkmnopprrtvwiQntMcOsLUsanvs" } ]
[ { "from": "human", "value": "In this task, you are given a country name and you need to return the calling code of the given country. Your output must be formatted as a plus sign (+), followed by the calling code number\nOne example is below.\nQ: Abkhazia\nA: +99544\nRationale: +99544 is the calling code of the country called Abkhazia.\nQ: South Africa\nA:" }, { "from": "gpt", "value": "+27" } ]
[ { "from": "human", "value": "Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.\n--------\nQuestion: Alice ceded a woman a win\n\nAnswer: Alice ceded a win to a woman\n\n\nQuestion: Bob screeched the man something\n\nAnswer: Bob screeched something to the man\n\n\nQuestion: Michael stated a man from work the case\n\nAnswer:" }, { "from": "gpt", "value": "Michael stated the case to a man from work\n\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you will be presented with a question having multiple possible answers in Swahili language. And you should choose a most suitable option out of \"A\", \"B\", \"C\", \"D\", and \"E\" based on your commonsense knowledge.\nInput: Question: Je! Unajenga nini unapofanya mazoezi ya nguvu? \n Options: A haja ya chakula B jasho C misuli D kiu E usawa \nOutput:" }, { "from": "gpt", "value": "D" } ]
[ { "from": "human", "value": "In this task you are expected to fix an SQL query based on feedback. You will be given an SQL statement and an English description with what is wrong about that SQL statement. You must correct the SQL statement based off of the feedback. 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. \n\nLet me give you an example: SQL: SELECT avg ( Area ) , max ( Capacity ) FROM stadium\nFeedback: Swap the average of \"Area\" with the average of \"Capacity\"\nThe answer to this example can be: SELECT avg(capacity) , max(capacity) FROM stadium\nHere is why: The SQL statement was adjusted to find the average of the capacity. This is a good example.\n\nOK. solve this:\nSQL: SELECT T1.title FROM Movie AS T1 JOIN Reviewer AS T2 JOIN Rating AS T3 ON T1.mID = T3.mID AND T3.rID = T2.rID WHERE T2.name = \"Steven Spielberg\"\nFeedback: in place of name, i want you to look for name.\nAnswer:" }, { "from": "gpt", "value": "SELECT title FROM Movie WHERE director = 'Steven Spielberg'" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a passage, 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 passage 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 passage or linked information.\nProblem:Passage: He had hoped to redshirt during the 2011 season, which was his freshman year, so that he could add size. He played in 2011 as a true freshman and got off to a modest start. Lockett only recorded four receptions for 50 yards, three rushes for nine yards, one kickoff return for ten yards, and two punt returns for a total of 13 yards in his first five games through October 8. Things started to turn around on October 15 when he posted a 100-yard return of a kickoff for a touchdown against Texas Tech. Over the ensuing weeks, he earned numerous Big 12 Conference honors for the 2011 team, including becoming a two-time Big 12 Special Teams Player of the Week. His first Player of the Week recognition came on October 24 after he produced a 251-yard all-purpose yards performance on October 22 against Kansas in the Governor's Cup that included posting a 97-yard kickoff return touchdown while becoming the first player in school history to return kickoffs for touchdowns in consecutive games and having a career-high five-reception 110-yard receiving day. His other Player of the Week recognition that season came on November 7 after a 315-yard all-purpose yard November 5 game against Oklahoma State that included an 80-yard kickoff return and three rushes for 84 yards as well as three receptions for 32 yards and a touchdown. Due to what was at first an undisclosed injury, he did not play in the final three games of Kansas State's regular season. Later, the injury was determined to be a lacerated kidney. In the four games before the injury, he had at least three receptions and 125 all-purpose yards in each game.\n Link Information: The Cowboys were led by seventh year head coach Mike Gundy Answer: Mike Gundy\nSolution:" }, { "from": "gpt", "value": "What was the name of the head coach of the team that Lockett played against on November 5th?" } ]
[ { "from": "human", "value": "In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.\n\nrbraQlcDoPVqXp, QjKraQlcDpX" }, { "from": "gpt", "value": "a, b, c, d, l, o, p, q, r, v, x" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence in Spanish, generate a new Spanish sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\n\nLa gente escribe en papel.\nOutput:" }, { "from": "gpt", "value": "La gente ya escribe en papel." } ]
[ { "from": "human", "value": "Q: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n9, 9, ['7173', 'v', 'h', '2189', '8653', 'w', 'K', 'y', '9307', '1955', '9025']\nA:" }, { "from": "gpt", "value": "9307" } ]
[ { "from": "human", "value": "Detailed Instructions: 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'.\nQ: Query: How do I get my free annual credit report? \n Clarification: did you want to know what the tenessee highway patrol cars look like\nA:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\nProblem:Title: Boxing Match. Sentence 1: Kevin was a boxer hoping to be champion. Sentence 2: He got his chance to challenge the current champ. Sentence 3: Kevin trained as hard as he could. Sentence 4: He devoted most of his time to it.\nSolution:" }, { "from": "gpt", "value": "They felt very betrayed by it." } ]
[ { "from": "human", "value": "This task is about translating a given English language sentence to French.\n\nQ: Let's jump ahead again.\n\nA: Faisons un nouveau saut.\n**\nQ: Shame.\n\nA: Dommage.\n\nQ: - To cut out the dead wood - Waiting\n\nA:" }, { "from": "gpt", "value": "De couper le bois mort J'attends...\n**\n" } ]
[ { "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\nDuring the rainy season in a city, the amount of sunlight in the city will (A) stay the same (B) decrease (C) expand (D) increase" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "In this task, you're given reviews from Amazon's products. Your task is to generate the Summary of the review.\nQ: A ugly shoe and so is the color\nA: " }, { "from": "gpt", "value": "Cheap item is not the best unless it is a mark down" } ]
[ { "from": "human", "value": "Teacher: 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nIsabella entered the hall. Olivia entered the hall. The apple is in the blue_treasure_chest. Olivia exited the hall. Isabella moved the apple to the green_basket. Where does Isabella think that Olivia searches for the apple?\nSolution: blue_treasure_chest\nReason: Since Olivia was no longer in the hall, she last remembers the apple being in the blue_treasure_chest even though Isabella moved it to the green_basket. Since Isabella was in the hall the entire time, she knows where Olivia will look for it.\n\nNow, solve this instance: Jack entered the basement. William entered the basement. The cabbage is in the green_bottle. Jack moved the cabbage to the green_bucket. Where will William look for the cabbage?\nStudent:" }, { "from": "gpt", "value": "green_bucket" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nThe input is a tweet which can be Hate Speech or Offensive. Given such a tweet, output a phrase from the tweet that makes it hate speech or offensive. The output should contain only one such phrase. The output has to be from within the tweet itself. Do not generate words or phrases not present in the tweet.\n\nseems like a nigger too from some of the speech patterns one of them rare dindus that can spell a lil bit\nOutput:" }, { "from": "gpt", "value": "nigger" } ]
[ { "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 the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\n\nTitle: Hugo's Hands. Sentence 1: Hugo was a skilled surgeon. Sentence 2: However, he was greedy and only did it for the money. Sentence 3: He did not care for his patients as long as he got paid. Sentence 4: One day, Hugo got into a car accident and broke both his hands.\nOutput:" }, { "from": "gpt", "value": "Steve looked great." } ]
[ { "from": "human", "value": "TASK DEFINITION: Construct a question that every answer in the list is correct and reasonable for it.\nPROBLEM: doctor, bathroom, bus, mall, movie, work\n\nSOLUTION: name a kind of place where it's easy to catch other people's germs.\n\nPROBLEM: gun, parasol, pitchfork, cane, fan, hat\n\nSOLUTION: name a prop you may hold in an \"olde time\" photograph at the fair.\n\nPROBLEM: muhammad ali, joe louis, j. cesar chavez, mike tyson, george foreman, sugar ray leon\n\nSOLUTION:" }, { "from": "gpt", "value": "past or present, name a boxing champion who was respected outside the ring as much as he was inside the ring.\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a math problem with context and a question and 5 answer choices, the task is to provide the correct answer choice based on the problem. You must choose one of the given answer choices by letter: a, b, c, d, or e; anything else is invalid.\nQ: Problem: the number 42 can be written as the sum of the squares of 3 different positive integers. what is the sum of these 3 integers ?\nOptions: a. 17, b. 10, c. 15, d. 14, e. 13\nA:" }, { "from": "gpt", "value": "b" } ]
[ { "from": "human", "value": "Part 1. Definition\nYou are given a science question (easy-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.\nPart 2. Example\nWhich part of a bicycle BEST moves in a circle? \n (A) Seat (B) Frame (C) Foot pedal (D) Kickstand\nAnswer: C\nExplanation: Seat, frame and Kickstand are static parts of the bicycle, even when bicycle moves. Foot pedal moves in a circle as bicycle moves.\nPart 3. Exercise\nHow does ice change the shape of rocks? \n (A) It dissolves the rocks by pooling on surfaces. (B) It breaks the rocks by expanding in openings. (C) It smooths the rocks by colliding with them. (D) It moves the rocks by pressing on them.\nAnswer:" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "In this task you will be given a list, of lists, of numbers. Each list is presented with brackets and comma-separated values. For example, a list of numbers is [1,2,3] and a list of two lists of numbers is [[1,2],[3,4,6]]. You should sum up the values at every position of every inner list and put it as an element of your answer, that is, you should sum the first members of each inner list together and put it as the first element of the list, then sum the second members of each inner list together and put it as the second element of your list, etc. The output should be a list of numbers with the same length as the longest inner list.\n--------\nQuestion: [[-45, -87, 52, -91, 90, -92, -32, -45, -96], [-23, -74, -88, 100], [31, -76, 58, 72, 42, 41, -91, 57], [-34, -33, 93, 53], [51, 22, -46, -77, 2, -86]]\n\nAnswer: [-20, -248, 69, 57, 134, -137, -123, 12, -96]\n\n\nQuestion: [[39, -89, -85, -96, -19, 62, -86], [85, -37, -100, 12, 81], [8, 100, -27, -94, 34, -91], [-64, -57, -26, 52, -36, 88, -41, -52], [-18, -83, -59, 48, 6, -37, -69]]\n\nAnswer: [50, -166, -297, -78, 66, 22, -196, -52]\n\n\nQuestion: [[25, -6, 62], [-82, -66, 10, -84], [50, -78, -48, -95, -32, 20, 6, 5, 88], [46, 76, 80, -37, -48, -6], [-69, 58, 76, 36, 57, -42]]\n\nAnswer:" }, { "from": "gpt", "value": "[-30, -16, 180, -180, -23, -28, 6, 5, 88]\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you have given an input which is agent's reply, based on that you have to identify what will be users' command for that reply. The user generally asks a question related to event scheduling or information of the scheduled events. Agent reply based on the available information or do the task as per user command.\n\nNext is your meeting with Jim tomorrow from 10:00 to 11:30 AM.\nOutput:" }, { "from": "gpt", "value": "What is after the oil change?" } ]
[ { "from": "human", "value": "In this task you will be given an arithmetic operation and you have to find its answer. The symbols of operators '+' and '-' has been swapped i.e you need to perform subtraction when you see a '+' symbol and addition in case of '-' symbol.\n\nExample Input: 9616 - 8145 + 562 + 3160 - 8906 - 360 + 9291 + 7609 + 460\nExample Output: 5945\n\nExample Input: 1724 - 4426 - 960 - 8997 - 5797 + 8037 - 7699 + 3023\nExample Output: 18543\n\nExample Input: 2300 + 6854 - 446 - 5417 + 1448\nExample Output:" }, { "from": "gpt", "value": "-139\n\n" } ]
[ { "from": "human", "value": "Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\n--------\nQuestion: I_TURN_RIGHT I_TURN_RIGHT\n\nAnswer: turn opposite right\n\n\nQuestion: I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_WALK\n\nAnswer: walk opposite right twice after look around right thrice\n\n\nQuestion: I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_RUN\n\nAnswer:" }, { "from": "gpt", "value": "walk right twice and run opposite right\n\n\n" } ]
[ { "from": "human", "value": "Definition: 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.\nInput: Command: eq { hop { argmax { all_rows ; score } ; team 1 } ; fc nantes ( d1 ) }, interpretation: select the row whose score record of all rows is maximum . the team 1 record of this row is fc nantes ( d1 ) .\nOutput:" }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "Q: Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".\nQuestion1: What are the best diet you know?, Question2: What is the best diet for someone that hates diets?\nA:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nSee one example below:\nProblem: Question: Are group 2 innate lymphoid cells ( ILC2s ) increased in chronic rhinosinusitis with nasal polyps or eosinophilia?\nAnswer: As ILC2s are elevated in patients with CRSwNP, they may drive nasal polyp formation in CRS. ILC2s are also linked with high tissue and blood eosinophilia and have a potential role in the activation and survival of eosinophils during the Th2 immune response. The association of innate lymphoid cells in CRS provides insights into its pathogenesis.\nSolution: yes\nExplanation: The answer clearly says that ICLSs are elevated, which is exactly what the question asks. Hence, the output will be yes and it is correct.\n\nProblem: Question: Does aspirin resistance determined with PFA-100 predict new thrombotic events in patients with stable ischemic cerebrovascular disease?\nAnswer: Aspirin resistance determined by PFA-100 does not predict new thrombotic events in patients with stable ischemic cerebrovascular disease.\nSolution:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Part 1. Definition\nTurn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"\nPart 2. Example\nFact: pesticides can harm animals.\nAnswer: What can harm animals?\nExplanation: It's a good question because it is formed by simply replacing the word \"pesticides\" with \"what\".\nPart 3. Exercise\nFact: pollen is made by haploid plants.\nAnswer:" }, { "from": "gpt", "value": "what makes pollen?" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact\n\nEnglish sentence: 16:37 Behold, I will gather all your lovers, with whom you have united, and all those whom you have loved, together with all those whom you have hated . And I will gather them together against you on every side . And I will uncover your disgrace before them, and they will see all your indecency .\nOutput:" }, { "from": "gpt", "value": "16:37 Bal eeg, Waxaan soo wada ururin doonaa kuwii ku caashaqi jiray oo dhan, cidda aad la midoobin, iyo kuwa dhan kan idiin jeclaaday, wada jir ah ula dhan kuwa aad neceb. Oo waxaan iyaga u soo ururiyo idinku soo jeedin doonaa dhinac kasta." } ]
[ { "from": "human", "value": "Instructions: In this task you are given a statement and an explanation giving you further knowledge about an entity in the statement. You must judge whether the statement is true or false based on the explanation. Label an instance as \"True\" if the explanation confirms the statement or doesn't disprove it. Label an instance as \"False\" if the explanation disproves the statement. The statement and explanation are separated by a newline character.\nInput: Tony Benn met former Liberal Prime Minister David Lloyd George when he was 12, and once shook hands with Mahatma Gandhi.\nTony Benn recalled that he met former Liberal Prime Minister David Lloyd George, while still a boy, he once shook hands with Mahatma Gandhi, in 1931, when his father was Secretary of State for India.\nOutput:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Given a sentence and two mentions from the text (arguments), indicate a phrase (a verb or noun phrase) that describes the relationship between the provided arguments.\n\nSentence: 'Num 21:8 And the LORD said unto Moses .', Argument/Subject 1: 'lord', Argument/Subject 2: 'mose'" }, { "from": "gpt", "value": "say to" } ]
[ { "from": "human", "value": "Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.\n\nExample input: Bob took the woman from work a cake\nExample output: Bob took a cake to the woman from work\nExample explanation: Input and output sentences have same meaning but different grammatical construction.\nQ: Michael quoted a woman a sentence\nA:" }, { "from": "gpt", "value": "Michael quoted a sentence to a woman" } ]
[ { "from": "human", "value": "Teacher:Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. For commands, 'left' and 'right' are used to denote the direction of an action. opposite turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. Actions and commands do not have quotations in the input and output.\nTeacher: Now, understand the problem? Solve this instance: I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT\nStudent:" }, { "from": "gpt", "value": "look around right twice and turn around left thrice" } ]
[ { "from": "human", "value": "You're given a sentence and your task is to classify whether the sentence is acceptable or not. Any sentence which is grammatically correct, has a naturalistic text, is written by a native speaker and which minimizes superfluous content is acceptable, otherwise unacceptable. If the sentence is acceptable then write \"acceptable\", otherwise \"unacceptable\".\n\nI went to the store and bought some whisky.\nacceptable\n\nWe contributed her our paycheck.\nunacceptable\n\nI put the book to Sally.\n" }, { "from": "gpt", "value": "unacceptable\n\n" } ]
[ { "from": "human", "value": "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.\n\n1, 3, ['g', '5347', 'H', '1875', '8583', '1939']" }, { "from": "gpt", "value": "g, 1875" } ]
[ { "from": "human", "value": "instruction:\nIn this task, you are given a question. Your task is to generate an answer that is relevant to the question.\nquestion:\nHave you ever been to the opera?\nanswer:\nI used to go once a month.\n\n\nquestion:\nDid you spend a lot of time building your career?\nanswer:\nI spent 6 years in the workforce in addition to college.\n\n\nquestion:\nDo you enjoy going to festivals?\nanswer:\n" }, { "from": "gpt", "value": "I have tickets to all the local ones.\n\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you are given a short passage that conveys a stereotype. A stereotype is an over-generalized belief about a particular group of people. You are expected to classify the passage into nine types of stereotype: race-color, socioeconomic, gender, disability, nationality, sexual-orientation, physical-appearance, religion, and age.\nInput: Passage: The other fighter fought hard and won, because black people are inherently stronger and more animal like than other races.\nOutput:" }, { "from": "gpt", "value": "race-color" } ]
[ { "from": "human", "value": "Q: Given a fact, create a question that can be answered using the fact. Construct the question such that it is unambiguous, has a unique answer and the answer can be given using the fact.\nFact: lack of food causes starvation\nA:" }, { "from": "gpt", "value": "A human who goes long periods of time without nourishment will experience?" } ]
[ { "from": "human", "value": "Teacher:In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nTeacher: Now, understand the problem? Solve this instance: Beginning: Kya wanted to be a model. Middle: She signed up with a local modeling agency. Ending: Kya found out that she was too short to be a model!\nStudent:" }, { "from": "gpt", "value": "Kya was 6 feet tall and ideal for the local modeling agency." } ]
[ { "from": "human", "value": "In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill.\nExample: Amends the Water Resources Development Act of 1999 to: (1) authorize appropriations for FY 1999 through 2009 for implementation of a long-term resource monitoring program with respect to the Upper Mississippi River Environmental Management Program (currently, such funding is designated for a program for the planning, construction, and evaluation of measures for fish and wildlife habitat rehabilitation and enhancement); (2) authorize the Secretary of the Army to carry out modifications to the navigation project for the Delaware River, Pennsylvania and Delaware, if such project as modified is technically sound, environmentally (currently, economically) acceptable, and economically justified; (3) subject certain previously deauthorized water resources development projects to the seven-year limitation governing project deauthorizations under the Act, with the exception of such a project for Indian River County, Florida; (4) except from a certain schedule of the non-Federal cost of the periodic nourishment of shore protection projects constructed after December 31, 1999, those projects for which a District Engineer's Report has been completed by such date; (5) require that the project cooperation agreement for the Comite River Diversion Project for flood control include a provision that specifies that any reduction in the non-Federal share that results from certain modifications be credited toward the share of project costs to be paid by the Amite River Basin Drainage and Water Conservation District; (6) allow the Secretary to provide additional compensation to Chesapeake City, Maryland (currently, to the City of Chesapeake, Maryland) for damage to its water supply resulting from the Chesapeake and Delaware Canal Project; (7) provide for the submission of certain reports on water resources development projects by the Secretary, notwithstanding Federal reporting termination provisions; and (8) authorize and provide for an authorization of appropriations for the existing program for the safety and operations expenses of the Federal Railroad Administration, and make available for obligation funds currently appropriated for such program.\nExample solution: To make technical corrections to the Water Resources Development Act of 1999.\nExample explanation: This Bill makes corrections to the Water Resources Development Act of 1999, hence the generated title is correct.\n\nProblem: Local Law Enforcement Hate Crimes Prevention Act of 2007 - (Sec. 3) Defines \"hate crime\" as a violent act causing death or bodily injury because of the actual or perceived race, color, religion, national origin, sexual orientation, gender, gender identity or disability of the victim.\n\n (Sec. 4) Authorizes the Attorney General, at the request of a state, local, or Tribal law enforcement agency, to provide technical, forensic, prosecutorial, or other assistance in the criminal investigation or prosecution of any crime that: (1) constitutes a crime of violence; (2) constitutes a felony under state, local, or Tribal laws; and (3) is motivated by prejudice based on the actual or perceived race, color, religion, national origin, gender, sexual orientation, gender identity, or disability of the victim or is a violation of the state, local, or Tribal hate crime laws. Requires the Attorney General to give priority for assistance to crimes committed by offenders who have committed crimes in more than one state and to rural jurisdictions that have difficulty covering extraordinary investigation or prosecution expenses.\n\nAuthorizes the Attorney General to award grants to state, local, and Indian law enforcement agencies for extraordinary expenses associated with the investigation and prosecution of hate crimes. Requires the Department of Justice Office of Justice Programs to work closely with grant recipients to ensure that the concerns and needs of all affected parties under the grant program are addressed.\n\nSets forth requirements and deadlines for grant applications. Limits grant amounts to $100,000 for any single jurisdiction in any one-year period.\n\nRequires the Attorney General to submit a report to Congress on the grant program by December 31, 2008.\n\nAuthorizes appropriations for FY2008-FY2009.\n\n(Sec. 5) Authorizes the Office of Justice Programs to award grants to state, local, or Tribal programs designed to combat hate crimes committed by juveniles. Authorizes appropriations.\n\n(Sec. 6) Authorizes appropriations for FY2008-FY2010 for additional personnel to prevent and respond to hate crime violations.\n\n(Sec. 7) Amends the federal criminal code to impose a fine and/or prison term of up to 10 years on any person who willfully causes bodily injury to any person, or who, through the use of fire, a firearm, or an explosive or incendiary device, attempts to cause bodily harm to any person, because of the actual or perceived race, color, religion, national origin, gender, sexual orientation, gender identity, or disability of such person.\n\nRequires certification by the Attorney General or other Department of Justice official of certain findings relating to an alleged hate crime prior to initiating a prosecution for such crime.\n\nExcludes evidence of expression or association of a defendant in a hate crime prosecution at trial, unless such evidence specifically relates to the offense being prosecuted.\n\n(Sec. 8) Provides that nothing in this Act shall be construed to prohibit expressive conduct or activities protected by the First Amendment.\n" }, { "from": "gpt", "value": "Solution: To provide Federal assistance to States, local jurisdictions, and Indian tribes to prosecute hate crimes, and for other purposes." } ]
[ { "from": "human", "value": "Instructions: In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\nInput: [-14, 63, 68, -67, -38, 48]\nOutput:" }, { "from": "gpt", "value": "[42, 126, 136, 201, 114, 96]" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, You are given a review of Amazon's food products. Your task is to divide them into two classes: negative or positive, depending on the content of the review.\nProblem:There earplugs were perfect. It is hunting season and my husband is a hunter, I love traveling with him, but hate shot gun noise. These are perfect fit and did not look bulky or noticeable. They sure did their job protecting my hearing and making a trip so much enjoyable and I could have a conversation and hear people too.\nSolution:" }, { "from": "gpt", "value": "positive" } ]
[ { "from": "human", "value": "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\nInput: Consider Input: Context: Kendall and Robin were in rival street gangs so during a fight, Kendall struck and broke both of Robin's legs with a baseball bat. \n Question: How would Robin feel as a result? \n Options: (A) in his life (B) angry that he was injured (C) hopeful for friendship with Kendall\n\nOutput: C\n\n\nInput: Consider Input: Context: Carson washed their hands of soot after a long work day. \n Question: How would Others feel as a result? \n Options: (A) quite lonely (B) quite in awe (C) hard working and polite\n\nOutput: A\n\n\nInput: Consider Input: Context: Cameron was cold so they wore sweaters more times than not. \n Question: What does Cameron need to do? \n Options: (A) give his sweaters away (B) buy some t shirts (C) buy some sweaters\n\n" }, { "from": "gpt", "value": "Output: A\n\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: 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.\nPROBLEM: you are ready i was born ready bayolover you are ready to sex\n\nSOLUTION: other\n\nPROBLEM: just for clean pots what will be left to clean up yes\n\nSOLUTION: other\n\nPROBLEM: have a relationship 1 love 2 trust 3 respect for each other you will become crazyfacewithtearsofjoy\n\nSOLUTION:" }, { "from": "gpt", "value": "happy\n\n" } ]
[ { "from": "human", "value": "You are given an original reference as well as a system reference. Your task is to judge the quality of the system reference. If the utterance is grammatically correct and fluent output 1, else output 0.\n\nEx Input:\nSystem Reference: chai yo thai restaurant is near nob hill.\nOriginal Reference: chai yo thai restaurant is near nob hill.\n\nEx Output:\n0\n\n\nEx Input:\nSystem Reference: what price range are you comfortable with?\nOriginal Reference: what is the price range i can help you find.\n\nEx Output:\n0\n\n\nEx Input:\nSystem Reference: what type of food would you like to eat?\nOriginal Reference: what food are you looking for.\n\nEx Output:\n" }, { "from": "gpt", "value": "0\n\n\n" } ]
[ { "from": "human", "value": "Definition: 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.\nInput: 1 tablespoon canola oil, 2 yellow onions, sliced, 2 shallots, sliced, 1 leek, sliced, 2 liters low sodium chicken broth, 12 cup reduced-fat swiss cheese, grated, 1 bunch fresh chives, finely chopped\nOutput:" }, { "from": "gpt", "value": "canola oil, yellow onions, shallots, liters, swiss cheese, fresh chives" } ]
[ { "from": "human", "value": "Given a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.\n\nInput: Consider Input: Premise: My son and I found a lot of dead bees in the swimming pool. \n Initial Context: We dried them out and dipped them into melted chocolate. \n Original Ending: We ate a bunch of chocolate covered bees. My son was 8 and told his school friends about it. They asked me to get them a batch. \n Counterfactual Context: We dried them out and threw them away.\n\nOutput: We ate a bunch of chocolate. My son was 8 and told his school friends about it. They asked me to get them a batch. \n\n\nInput: Consider Input: Premise: Johnny, 18 was attracted to Julie, 35. \n Initial Context: Julie thought Johnny was too young to approach her. \n Original Ending: But Johnny walked up to her at her job and asked her on a date. Julie accepted because Johnny had a luxury truck. They made love because Julie didn't fight her feelings. \n Counterfactual Context: Julie had no interest in Johnny because she was a lesbian.\n\nOutput: But Johnny walked up to her at her job and asked her for a drive. Julie accepted because Johnny had a luxury truck. They drove around because Julie didn't fight her feelings. \n\n\nInput: Consider Input: Premise: Carlos has been single for several Year's. \n Initial Context: One day Carlos and his friend Dan go to a dance club. \n Original Ending: Carlos meets a nice girl there and they exchange phone numbers. The next week they go out for a cup of coffee. Carlos hopes he has finally met someone he can love. \n Counterfactual Context: One day Carlos and his friend decided not to go to their usual dance club.\n\n" }, { "from": "gpt", "value": "Output: Carlos meets a nice girl there and they exchange phone numbers. The next week they go out for a cup of coffee. Carlos hopes he has finally met someone he can love. \n\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets. A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.\nTeacher: Now, understand the problem? Solve this instance: Set1: '{2, 4, 7, 9, 20}', Set2: '{1, 5, 10, 12, 13, 14, 18, 20}'. Is the element '13' in the intersection of Set1 and Set2 ?\nStudent:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Galician. Your job is to translate the Galician sentence into Spanish.\nProblem:Tres veces\nSolution:" }, { "from": "gpt", "value": "El triple." } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given a sentence from a conversation between a human and a virtual assistant. Your task is to identify which one of following five services the sentence is related to - Media, Travel, Flights, Buses, RideSharing\n\nHello! Please can you suggest me some attractions to visit for I've a couple of days holidays this week?\n" }, { "from": "gpt", "value": "Travel" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\nProblem:Jolly Molly\nSolution:" }, { "from": "gpt", "value": "jolly molly go to bolly buy a skateboard try an ollie lose her hat drop her dolly she fell splat right on her collie collie yell your off your trolly he bite molly on herlolly that's why molly be n't jolly by golly" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a 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: Gosh-darned, all this modern equal rights is silly, we need to bring back the 40's and 50's! Women's place in in the kitchen, segregation was all the rage, and ignorance was bliss...\nOutput:" }, { "from": "gpt", "value": "Toxic" } ]
[ { "from": "human", "value": "Given a sentence, generate a most unlikely next statement. The next statement should not be logically relevant to the given context\n\nThe young male takes his hand and reaches inside to grab the soccer ball. As they keep playing, a set of feet\nfalls off the ground.\n\nShe looks at someone as he stares out the windshield. She\npours the soda in her car, then wipes it away with the back of her hand.\n\nHe follows it into the woods. Someone\n" }, { "from": "gpt", "value": "licks her fingertip and looks around at the dog.\n\n" } ]
[ { "from": "human", "value": "Q: Given a sentence in Italian, generate a new Italian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nSe si vuole leggere un gatto allora si dovrebbe procedere a cazzo rh.\nA:" }, { "from": "gpt", "value": "Se vuoi raccogliere un libro, allora dovresti andare all'inferno, cazzo." } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGiven 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).\nExample: Entity 1: plant \n Entity 2: leaf\nOutput: yes\nThe answer is correct. Because the leaf is part of the plant. Therefore, here leaf is meronym and the plant is holonym.\n\nNew input case for you: Entity 1: pupas \n Entity 2: alkaline groundwater\nOutput:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "instruction:\nYou 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.\nquestion:\npassword = Ginwww1WvOJkPMPgfLj\nanswer:\n1\n\n\nquestion:\npassword = fQDJbMgacnKNaWUn6TP.w0WdyXncLBlcYxEj\nanswer:\n16\n\n\nquestion:\npassword = 0GJLsbOM.SHP!aqGMivXWkLWh59atFPkP02dii1ZSjWlabaQ.\nanswer:\n" }, { "from": "gpt", "value": "29\n\n\n" } ]
[ { "from": "human", "value": "Given a context passage, generate a question from the passage such that its answer is shortest continous span from the passage.\n--------\nQuestion: Nations that have more industry produce more hazardous waste. Currently, the United States is the worlds largest producer of hazardous wastes, but China, which produces so many products for the developed world, may soon take over the number-one spot. Countries with more industry produce more hazardous wastes than those with little industry. Problems with haz- ardous wastes and their disposal became obvious sooner in the developed world than in the developing world. As a result, many developed nations, including the United States, have laws to help control hazardous waste disposal and to clean toxic sites. As mentioned in the \"Impacts of Hazardous Waste\" concept, the Superfund Act requires companies to clean up contaminated sites that are designated as Superfund sites (Figure 1.1). If a responsible party cannot be identified, because the company has gone out of business or its culpability cannot be proven, the federal government pays for the cleanup out of a trust fund with money put aside by the petroleum and chemical industries. As a result of the Superfund Act, companies today are more careful about how they deal with hazardous substances. Superfund sites are located all over the nation and many are waiting to be cleaned up. The Resource Conservation and Recovery Act of 1976 requires that companies keep track of any hazardous materials they produce. These materials must be disposed of using government guidelines and records must be kept to show the government that the wastes were disposed of safely. Workers must be protected from the hazardous materials. To some extent, individuals can control the production and disposal of hazardous wastes. We can choose to use materials that are not hazardous, such as using vinegar as a cleanser. At home, people can control the amount of pesticides that they use (or they can use organic methods of pest control). It is also necessary to dispose of hazardous materials properly by not pouring them over the land, down the drain or toilet, or into a sewer or trashcan. Click image to the left or use the URL below. URL:\n\nAnswer: this country is currently the largest producer of hazardous waste.\n\n\nQuestion: Almost all surfaces reflect some of the light that strikes them. The still water of the lake in Figure 22.9 reflects almost all of the light that strikes it. The reflected light forms an image of nearby objects. An image is a copy of an object that is formed by reflected or refracted light. If a surface is extremely smooth, like very still water, then an image formed by reflection is sharp and clear. This is called regular reflection. If the surface is even slightly rough, an image may not form, or if there is an image, it is blurry or fuzzy. This is called diffuse reflection. Both types of reflection are represented in Figure 22.10. You can also see animations of both types of reflection at this URL: [Link] In Figure 22.10, the waves of light are represented by arrows called rays. Rays that strike the surface are referred to as incident rays, and rays that reflect off the surface are known as reflected rays. In regular reflection, all the rays are reflected in the same direction. This explains why regular reflection forms a clear image. In diffuse reflection, in contrast, the rays are reflected in many different directions. This is why diffuse reflection forms, at best, a blurry image. One thing is true of both regular and diffuse reflection. The angle at which the reflected rays bounce off the surface is equal to the angle at which the incident rays strike the surface. This is the law of reflection, and it applies to the reflection of all light. The law is illustrated in Figure 22.11 and in the animation at this URL: Mirrors are usually made of glass with a shiny metal backing that reflects all the light that strikes it. Mirrors may have flat or curved surfaces. The shape of a mirrors surface determines the type of image the mirror forms. For example, the image may be real or virtual. A real image forms in front of a mirror where reflected light rays actually meet. It is a true image that could be projected on a screen. A virtual image appears to be on the other side of the mirror. Of course, reflected rays dont actually go behind a mirror, so a virtual image doesnt really exist. It just appears to exist to the human eye and brain. Most mirrors are plane mirrors. A plane mirror has a flat reflective surface and forms only virtual images. The image formed by a plane mirror is also life sized. But something is different about the image compared with the real object in front of the mirror. Left and right are reversed. Look at the man shaving in Figure 22.12. He is using his right hand to hold the razor, but his image appears to be holding the razor in the left hand. Almost all plane mirrors reverse left and right in this way. Some mirrors have a curved rather than flat surface. Curved mirrors can be concave or convex. A concave mirror is shaped like the inside of a bowl. This type of mirror forms either real or virtual images, depending on where the object is placed relative to the focal point. The focal point is the point in front of the mirror where the reflected rays intersect. You can see how concave mirrors form images in Figure 22.13 and in the interactive animation at the URL below. The animation allows you to move an object to see how its position affects the image. Concave mirrors are used behind car headlights. They focus the light and make it brighter. They are also used in some telescopes. The other type of curved mirror, a convex mirror, is shaped like the outside of a bowl. This type of mirror forms only virtual images. The image is always right-side up and smaller than the actual object, which makes the object appear farther away than it really is. You can see how a convex mirror forms an image in Figure 22.14 and in the animation at the URL below. Because of their shape, convex mirrors can gather and reflect light from a wide area. This is why they are used as side mirrors on cars. They give the driver a wider view of the area around the vehicle\n\nAnswer: Concave mirrors are used\n\n\nQuestion: The Rams started their season on the road against the Lions. The Rams drew first blood in the first quarter with a 48-yard field goal from Greg Zuerlein to take a 3-0 lead for the only score of that quarter. The Lions then took a 7-3 lead with Joique Bell's 1-yard run for a touchdown in the 2nd quarter. The Rams responded with a 29-yard field goal from Zuerlein as they came up within a point 7-6 before on the Lions' next possession, Matthew Stafford was picked off by Cortland Finnegan and it was returned 31 yards for a touchdown as the Rams retook the lead 13-7. The Lions then responded with Jason Hanson kicking a 41-yard field goal to shorten the Rams' lead to 13-10 at halftime. After the break, the Lions scored first with Jason Hanson kicking a 45-yard field goal to tie the game 13-13 for the only score of the 3rd quarter. However, the Rams moved back into the lead in the 4th quarter with Brandon Gibson's 23-yard catch from Sam Bradford to make it 20-13. The Lions tied the game back up with Kevin Smith running for a touchdown from 5 yards out to tie the game 20-20. The Rams then retook the lead with Greg Zuerlein kicking a 46-yard field goal to make the score 23-20. On their last possession, the Lions moved down the field and Matthew Stafford found Kevin Smith on a 5-yard touchdown pass to make the final score 27-23 as the Rams began their season 0-1.\n\nAnswer:" }, { "from": "gpt", "value": "Who kicked the longest field goal in the last quarter?\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a dialogue from a conversation between an agent and a customer. Your task is to determine the speaker of the dialogue. Answer with \"agent\" or \"customer\".\n\nLet me give you an example: Hello. How may I aid you today?\nThe answer to this example can be: agent\nHere is why: This is a pretty straightforward dialogue, and the speaker wants to help the other. So, the agent is the speaker.\n\nOK. solve this:\nI am Margaret Clark.\nAnswer:" }, { "from": "gpt", "value": "customer" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence.\nPROBLEM: Sentence: 'a big pile of pizzas that are in pans'. Count the number of vowels in the given sentence.\n\nSOLUTION: 12\n\nPROBLEM: Sentence: 'a red and white no parking sign stands slanted near some trees'. Count the number of consonants in the given sentence.\n\nSOLUTION: 33\n\nPROBLEM: Sentence: 'they are taking a picture with your skis and snow equipment on'. Count the number of consonants in the given sentence.\n\nSOLUTION:" }, { "from": "gpt", "value": "31\n\n" } ]
[ { "from": "human", "value": "In this task, you are given an input i,A where i is an integer and A is an array. You need to find every ith element of A starting with the 1st element.\n\n2, ['6295', '6721', '5185', '8073', 'l', 'g', 'h', 'A', '4451', 'D', '3843', '5835', '1237', '1991', '6987', 'E', '8493', 'b', '9809', 'l', 'G', '7417', 'W', '179', '971', 'W', 'V', '7329', '9215', 'H', 'D', '9925']" }, { "from": "gpt", "value": "6295, 5185, l, h, 4451, 3843, 1237, 6987, 8493, 9809, G, W, 971, V, 9215, D" } ]
[ { "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: Seven young men on the beach playing a game of balance and skill involving concentric circles drawn in the sand about three feet apart. Sentence 2: People are outside on the beach\nOutput:" }, { "from": "gpt", "value": "Young men are in a competition on the beach" } ]
[ { "from": "human", "value": "You will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings.\n\nExample input: How do you remove keys from a computer keyboard for cleaning?\nExample output: Place the tip of your finger under the corner of a key and gently twist to pop it off.\nExample explanation: The answer is related to the question, but certainly doesn't lead to the asked outcome( A sharp narrow object should be used instead of finger.), so this is a correct answer.\nQ: how do you use the internet on an iphone?\nA:" }, { "from": "gpt", "value": "pull down the search bar and type in the website you need." } ]
[ { "from": "human", "value": "In this task, you need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence.\n\nInput: Consider Input: Sentence: 'a crew of people looking at an airplane'. Count the number of vowels in the given sentence.\n\nOutput: 15\n\n\nInput: Consider Input: Sentence: 'a bird sitting on a tree branch with a berry in its mouth'. Count the number of consonants in the given sentence.\n\nOutput: 29\n\n\nInput: Consider Input: Sentence: 'a dog next to a christmas tree with presents'. Count the number of consonants in the given sentence.\n\n" }, { "from": "gpt", "value": "Output: 24\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: threat and non-threat. Threat is a statement that someone will be hurt or harmed, especially if the person does not do something in particular.\n\nComment: Enough already. Cut the head off this snake.\nSolution: Threat\nWhy? This comment conveys a violent threat to someone.\n\nNew input: Comment: If somebody shoots the bastard I will start a defense council fund on Gofundme for our hero\nSolution:" }, { "from": "gpt", "value": "Threat" } ]
[ { "from": "human", "value": "Q: Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nThe artist Lee Krasner who used to cut her own paintings to create collages was married to which other artist?\nA:" }, { "from": "gpt", "value": "jackson pollock" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is potentially offensive to anyone (i.e., a subset of people, any particular person, etc.), 2) no, otherwise. Note that potentially offensive posts can contain sexual, racial, religious biased or offensive language. Warning: the examples and instances may contain offensive language.\n\nNiggaz been making trash lately. Well not everybody but some lol\n" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a sentence containing a particular emotion. You must classify the sentence into one of the six emotions: 'joy', 'love', 'anger', 'fear', or 'surprise'.\nProblem:i i have all the predictable feelings loki is that guy i know from many many other fandoms im not impressed with me for my loki feelings\nSolution:" }, { "from": "gpt", "value": "surprise" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to count the number of words in a sentence that contain the given letter\nProblem:Sentence: 'a white plate topped with pizza on a blue table'. How many words contain the letter 'v' in the sentence.\nSolution:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a sentence and a question, you would be asked to create the answer which is contained in the sentence provided.\n\nSentence: Food is glucose used for the bacteria. Question: What is glucose used for the bacteria?\nOutput:" }, { "from": "gpt", "value": "food" } ]
[ { "from": "human", "value": "In this task, you are given a sentence from the research paper and your task is to classify the given sentence into the following categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \nQ: Recently , an increasing number of studies have highlighted the promising effects of NM in inhibiting cancer progression.\nA: " }, { "from": "gpt", "value": "background" } ]
[ { "from": "human", "value": "In this task, you will be given a sentence or two along with a change aspect. You should change the given text in the given aspect. Aspects are explained below:\n Tense: Change the tense of the verbs in the text. If they're in past tense, change them to present, and if they're in present tense, change them to past tense.\nNumber: Change the number of the nouns in the given text. Make plurals into singles and single into plurals. Remember to change the corresponding pronouns accordingly.\nVoice: If the verbs are in active voice, change them to be passive, otherwise, change them to be in active voice.\nAdverb: add one or multiple adverbs to the text.\nGender: If the text contains female names and pronouns, substitute them with male names and pronouns. Do the same for sentences with mala names and pronouns.\n\nsentence: Kirilov ceded the presidency to Shatov because he was more popular . aspect: Tense" }, { "from": "gpt", "value": "Kirilov is ceding the presidency to Shatov because he is more popular ." } ]
[ { "from": "human", "value": "In this task, you're given two sentences, sentence 1 and sentence 2, and the genre they belong to. Your job is to determine if the two sentences belong to the same genre or not. Indicate your answer with Y and N respectively. Genres available include: face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction. Sentences belonging to 'face-to-face' genres relate to conversations or dialogues, 'government' encompasses information released from public government websites, 'letters' refers to any written work for philanthropic fundraising, '9/11' relates to information pertaining to the 9/11 attacks, 'oup' includes non-fiction works on the textile industry and child development, 'slate' refers to any cultural topic that appears in the slate magazine, 'telephone' includes telephonic dialogue, 'travel' deals with information in travel guides, 'verbatim' includes short posts regarding linguistics, and 'fiction' includes popular works of fiction like 'The Secret Adversary' etc.\nQ: Sentence 1: The interior is cavernous, but the caves have suffered from centuries of vandalism. Sentence 2: There's no more loyalty among the students. Genre: slate.\nA: " }, { "from": "gpt", "value": "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 sentence which is either in the Hindi language or English language. You task is to identify the language of input sentence. Input sentence can be in Hindi or English language only and also it cannot have two languages at a time.\n\nThe first two were found unreliable and the prosecution case rested mainly on the evidence of the remaining five approvers .\nSolution: English\nWhy? Input sentence is in English language as all the characters are of English alphabets only.\n\nNew input: If you want information on any NHS service , ring the Health Information Service on 0800-665544 .\nSolution:" }, { "from": "gpt", "value": "English" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False.\nPart 2. Example\nPassage: Madonna released the Material Girl clothing line, which she designed with her daughter, Lourdes. The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label. Madonna also opened a series of fitness centers around the world named Hard Candy Fitness. In November 2011, Madonna and MG Icon announced the release of a second fashion brand called Truth or Dare by Madonna to include footwear, underclothing, and accessories. She also directed her second feature film, W.E., a biographic about the affair between King Edward VIII and Wallis Simpson; it was co-written with Alek Keshishian. Critical and commercial response to the film was negative. Madonna contributed the ballad \"Masterpiece\" for the film's soundtrack, which won her a Golden Globe Award for Best Original Song. Question: Material Girl clothing line is released under which brand?\nAnswer: True\nExplanation: The answer to given question is 'Macy's', which can be determined from the second sentence of the paragraph \"The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label\". Since this question is answerable, the output is True.\nPart 3. Exercise\nPassage: where is the mass of the object, is the velocity of the object and is the distance to the center of the circular path and is the unit vector pointing in the radial direction outwards from the center. This means that the unbalanced centripetal force felt by any object is always directed toward the center of the curving path. Such forces act perpendicular to the velocity vector associated with the motion of an object, and therefore do not change the speed of the object (magnitude of the velocity), but only the direction of the velocity vector. The unbalanced force that accelerates an object can be resolved into a component that is perpendicular to the path, and one that is tangential to the path. This yields both the tangential force, which accelerates the object by either slowing it down or speeding it up, and the radial (centripetal) force, which changes its direction. Question: Where does the centripetal force come from?\nAnswer:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Definition: 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.\nInput: Category: LOW COUNTRIES \nClue: In 1995 Dutch peacekeeping troops were taken hostage at Srebrenica in this country\nOutput:" }, { "from": "gpt", "value": "bosnia" } ]
[ { "from": "human", "value": "Definition: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with 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: Downward view of a man with an orange helmet climbing a rock. Sentence 2: A picture is taken from below as a woman climbs\nOutput:" }, { "from": "gpt", "value": "A man with an orange helmet climbs a rock." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two natural language statements with similar wording. You must choose the statement that makes less sense based on common sense knowledge. A '\n' separates the statements. Use \"first\" or \"second\" to indicate which sentence makes less sense.\nProblem:we can borrow money from a toilet\nwe can borrow money from a bank\nSolution:" }, { "from": "gpt", "value": "first" } ]
[ { "from": "human", "value": "In this task, you will be shown a conversation. You need to write a question with three choices for the conversation. Your question should be answerable based on the conversation and only have one correct answer. Note that you don't need to answer your question. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nQ: F: What color are these flowers? M: They are yellow.\nA: " }, { "from": "gpt", "value": "What color are these flowers? (A) Red (B) Yellow (C) Blue" } ]
[ { "from": "human", "value": "Teacher: In 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nBeginning: Helen lived in the state of Washington. Middle: Helen planned to drive to Canada but it started snowing heavily.\nSolution: Helen stayed home instead and planned to go another day.\nReason: Generally, people prefer not to drive in bad weather.\n\nNow, solve this instance: Beginning: Anna won a pair of tickets for a cruise. Middle: She brought her disabled husband with her.\nStudent:" }, { "from": "gpt", "value": "Anna had to take care of him the entire trip." } ]
[ { "from": "human", "value": "Given a scientific question and its correct answer, generate supporting facts for the answer. This supporting fact can be an explanation for the answer to the given question.\n\nQuestion: Where is pedocal soil commonly found? Answer: grasslands" }, { "from": "gpt", "value": "Pedocal is the soil common in grasslands. The more arid climate increases calcium in the soil. Pedocal is not as fertile." } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a paragraph and title from the research paper. Your task is to classify whether the given title is suitable or not for the research paper based on the given paragraph. Return \"True\" if title is proper according to paragraph else \"False\".\nInput: Paragraph: The fusion subunit of the SARS-CoV S glycoprotein contains two regions of hydrophobic heptad-repeat amino acid sequences that have been shown in biophysical studies to form a six-helix bundle structure typical of the fusion-active core found in Class I viral fusion proteins. Here, we have applied serine-scanning mutagenesis to the C-terminal-most heptad-repeat region in the SARS-CoV S glycoprotein to investigate the functional role of this region in membrane fusion. We show that hydrophobic sidechains at a and d positions only within the short helical segment of the C-terminal heptad-repeat region (I1161, I1165, L1168, A1172, and L1175) are critical for cell -cell fusion. Serine mutations at outlying heptad-repeat residues that form an extended chain in the core structure (V1158, L1179, and L1182) do not affect fusogenicity. Our study provides genetic evidence for the important role of a-helical packing in promoting S glycoprotein-mediated membrane fusion. D \n Title: Serine-scanning mutagenesis studies of the C-terminal heptad repeats in the SARS coronavirus S glycoprotein highlight the important role of the short helical region\nOutput:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Q: In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nMiddle: After 1000 digits, Rick ran out of steam. Ending: But he enjoyed it so much.\nA:" }, { "from": "gpt", "value": "Rick was memorizing all of digits of pi." } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2. If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.\n\n[-2, 82, -59, -3, 19, 35, 67]\n[6, 164, 177, 9, 38, 70, 134]\n\n[-49, -11, -28, 44, 16, -10, -77, 13, 23]\n[147, 33, 84, 88, 32, 30, 231, 26, 46]\n\n[-16, -36, -24, 42, 73, -14]\n" }, { "from": "gpt", "value": "[48, 108, 72, 84, 146, 42]\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is intentionally offensive, 2) no, otherwise. Also, generate label 'no' for offensive statements that appear to be unintentional, or non-offensive statements that are underhandedly offensive. Warning: the examples and instances may contain offensive language.\nInput: You hoes give me more and more reasons everyday to stay my ass single for another 2 years\nOutput:" }, { "from": "gpt", "value": "Yes" } ]

Subsets and Splits

No community queries yet

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