Datasets:

connections-dev
/

connection_queries_jan12_natural_iterate1_1_reason_medium_0.7_1024_gpt-5-mini-20

triple1 listlengths 3 3	triple2 listlengths 3 3	triple3 listlengths 3 3	triple1_labels listlengths 3 3	triple2_labels listlengths 3 3	triple3_labels listlengths 3 3	description stringlengths 8 19	keep_triple bool 1 class	query_prompt stringlengths 3.23k 3.36k	query stringlengths 85 226	entity_a stringlengths 3 55	entity_b stringlengths 4 85	rel_b stringclasses 88 values	index int64 0 930	prompt listlengths 3 3	path_prediction listlengths 1 1	prompt_for_path listlengths 1 1	all_response_tokens listlengths 1 1	all_reasoning_tokens listlengths 1 1	response_1 stringlengths 104 14.8k	parsed_paths stringlengths 81 8.02k	iterate_prompt_1 listlengths 3 3	path_prediction_old_{counter} listlengths 1 1	prompt_for_path_old_{counter} listlengths 1 1	usage listlengths 1 1
[ "Q1352656", "P166", "Q935843" ]	[ "Q356715", "P166", "Q935843" ]	[ "Q356715", "P358", "Q100871850" ]	[ "Morton Gould", "award received", "Grammy Lifetime Achievement Award" ]	[ "Benny Carter", "award received", "Grammy Lifetime Achievement Award" ]	[ "Benny Carter", "discography", "Benny Carter discography" ]	Q935843__P166	false	Task: Generate a Natural Language Query. You will be given input in the following format: Concept A: entity1 Concept B: entity2 Concept C: (concept B, rel, entity3) Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess. You...	What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?	Morton Gould	Benny Carter discography	discography	0	[ { "content": "Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factua...	[ "<answer>\n{\n1: [\n [\"Morton Gould\", \"performed at\", \"Carnegie Hall\"],\n [\"Carnegie Hall\", \"featured\", \"Benny Carter\"],\n [\"Benny Carter\", \"discography\", \"Benny Carter discography\"]\n],\n2: [\n [\"Morton Gould\", \"conducted\", \"New York Philharmonic\"],\n [\"New York Philharmonic\", \"comm...	[ [ { "content": "Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence o...	[ 5057 ]	[ 4416 ]	<think> Mapping connections between composers I’m trying to produce multiple pathways connecting Morton Gould to Benny Carter, ultimately leading to a final triple that includes Carter's discography. I need a diverse range of connections, like their collaborations, shared orchestras, and involvement with ASCAP. Go...	<answer> { 1: [ ["Morton Gould", "born in", "New York City"], ["New York City", "birthplace of", "Benny Carter"], ["Benny Carter", "discography", "Benny Carter discography"] ], 2: [ ["Morton Gould", "has article on", "Wikipedia"], ["Wikipedia", "has article on", "Benny Carter"], ["Benny Carter", "discograph...	[ { "content": "Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factua...	[ "<think>\nMapping connections between composers\n\nI’m trying to produce multiple pathways connecting Morton Gould to Benny Carter, ultimately leading to a final triple that includes Carter's discography. I need a diverse range of connections, like their collaborations, shared orchestras, and involvement with A...	[ "Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, ...	[ { "completion_tokens": 3262, "prompt_tokens": 1587, "total_tokens": 4849 } ]
[ "Q57067", "P166", "Q38104" ]	[ "Q131729", "P166", "Q38104" ]	[ "Q131729", "P106", "Q593644" ]	[ "Max von Laue", "award received", "Nobel Prize in Physics" ]	[ "William Lawrence Bragg", "award received", "Nobel Prize in Physics" ]	[ "William Lawrence Bragg", "occupation", "chemist" ]	Q38104__P166	false	Task: Generate a Natural Language Query. You will be given input in the following format: Concept A: entity1 Concept B: entity2 Concept C: (concept B, rel, entity3) Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess. You...	What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?	Max von Laue	chemist	occupation	1	[ { "content": "Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is...	[ "<answer>\n{\n1: [\n [\"Max von Laue\", \"discovered\", \"X-ray diffraction\"],\n [\"X-ray diffraction\", \"used by\", \"Kathleen Lonsdale\"],\n [\"Kathleen Lonsdale\", \"occupation\", \"chemist\"]\n],\n2: [\n [\"Max von Laue\", \"discovered\", \"X-ray diffraction\"],\n [\"X-ray diffraction\", \"enabled\", \"p...	[ [ { "content": "Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection...	[ 8375 ]	[ 7872 ]	<think> Evaluating paths for accuracy I’m finding this a bit speculative, and I worry about keeping everything factually accurate. The user is looking for many valid paths, but I want to focus on quality, avoiding any false claims. I think I’ll stick to producing 8-10 solid paths. I've identified a few paths that ...	<answer> { 1: [ ["Max von Laue", "professor at", "University of Berlin"], ["University of Berlin", "professor", "Emil Fischer"], ["Emil Fischer", "occupation", "chemist"] ], 2: [ ["Max von Laue", "professor at", "University of Berlin"], ["University of Berlin", "professor", "Richard Willstätter"], ["Richard...	[ { "content": "Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is...	[ "<think>\nEvaluating paths for accuracy\n\nI’m finding this a bit speculative, and I worry about keeping everything factually accurate. The user is looking for many valid paths, but I want to focus on quality, avoiding any false claims. I think I’ll stick to producing 8-10 solid paths. I've identified a few pat...	[ "Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of fa...	[ { "completion_tokens": 6493, "prompt_tokens": 1461, "total_tokens": 7954 } ]
[ "Q2085", "P161", "Q164328" ]	[ "Q2085", "P161", "Q174263" ]	[ "Q174263", "P19", "Q268873" ]	[ "Twin Peaks", "cast member", "David Koechner" ]	[ "Twin Peaks", "cast member", "Rodney Rowland" ]	[ "Rodney Rowland", "place of birth", "Newport Beach" ]	Q2085__P161	false	Task: Generate a Natural Language Query. You will be given input in the following format: Concept A: entity1 Concept B: entity2 Concept C: (concept B, rel, entity3) Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess. You...	What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?	David Koechner	Newport Beach	place of birth	2	[ { "content": "Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relatio...	[ "<answer>\n{\n1: [\n [\"David Koechner\", \"co-star\", \"Steve Carell\"],\n [\"Steve Carell\", \"worked with\", \"Actor A\"],\n [\"Actor A\", \"place of birth\", \"Newport Beach\"]\n],\n2: [\n [\"David Koechner\", \"acted with\", \"John C. Reilly\"],\n [\"John C. Reilly\", \"directed by\", \"Director B\"],\n ...	[ [ { "content": "Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head,...	[ 3586 ]	[ 0 ]	<answer>{ 1: [ ["David Koechner", "co-star", "Will Ferrell"], ["Will Ferrell", "co-founded", "Funny or Die"], ["Funny or Die", "employed", "Adam Brody"], ["Adam Brody", "place of birth", "Newport Beach"] ], 2: [ ["David Koechner", "acted in", "Anchorman"], ["Anchorman", "starred", "Will Ferrell"], ["Will ...	<answer> { 1: [ ["David Koechner", "co-star", "Will Ferrell"], ["Will Ferrell", "co-founded", "Funny or Die"], ["Funny or Die", "employed", "Adam Brody"], ["Adam Brody", "place of birth", "Newport Beach"] ], 2: [ ["David Koechner", "acted in", "Anchorman"], ["Anchorman", "starred", "Will Ferrell"], ["Will...	[ { "content": "Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relatio...	[ "<answer>{\n1: [\n [\"David Koechner\", \"co-star\", \"Will Ferrell\"],\n [\"Will Ferrell\", \"co-founded\", \"Funny or Die\"],\n [\"Funny or Die\", \"employed\", \"Adam Brody\"],\n [\"Adam Brody\", \"place of birth\", \"Newport Beach\"]\n],\n2: [\n [\"David Koechner\", \"acted in\", \"Anchorman\"],\n [\"Anch...	[ "Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) form...	[ { "completion_tokens": 3460, "prompt_tokens": 2235, "total_tokens": 5695 } ]
[ "Q18037479", "P2293", "Q11081" ]	[ "Q18053558", "P2293", "Q11081" ]	[ "Q18053558", "P2548", "Q22809711" ]	[ "CD2AP", "genetic association", "Alzheimer's disease" ]	[ "ATXN7L1", "genetic association", "Alzheimer's disease" ]	[ "ATXN7L1", "strand orientation", "reverse strand" ]	Q11081__P2293	false	"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)	"What are different ways of connecting CD2AP, a protein involved in cellular processes, and a substa(...TRUNCATED)	CD2AP	reverse strand	strand orientation	3	[{"content":"Query: What are different ways of connecting CD2AP, a protein involved in cellular proc(...TRUNCATED)	["<answer>{\n \"1\": [\n [\"CD2AP\", \"binds\", \"cortactin (CTTN)\"],\n [\"cortactin (CTTN)\(...TRUNCATED)	[[{"content":"Query: What are different ways of connecting CD2AP, a protein involved in cellular pro(...TRUNCATED)	[ 8218 ]	[ 7104 ]	"<think>\nLinking strand orientations\n\nI need to create paths that connect CD2AP to a final tr(...TRUNCATED)	"<answer>\ntags as instructed and aim for 15 unique paths while avoiding repetition of the same trip(...TRUNCATED)	[{"content":"Query: What are different ways of connecting CD2AP, a protein involved in cellular proc(...TRUNCATED)	["<think>\nLinking strand orientations\n\nI need to create paths that connect CD2AP to a final t(...TRUNCATED)	["Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and (...TRUNCATED)	[ { "completion_tokens": 6294, "prompt_tokens": 2087, "total_tokens": 8381 } ]
[ "Q283572", "P463", "Q254138" ]	[ "Q316136", "P463", "Q254138" ]	[ "Q316136", "P19", "Q39709" ]	[ "Kun Nong", "member of", "Slipknot" ]	[ "Chris Fehn", "member of", "Slipknot" ]	[ "Chris Fehn", "place of birth", "Des Moines" ]	Q254138__P463	false	"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)	What are different ways of connecting Kun Nong and someone who was born in Des Moines?	Kun Nong	Des Moines	place of birth	4	[{"content":"Query: What are different ways of connecting Kun Nong and someone who was born in Des M(...TRUNCATED)	["<answer>\n{\n\"1\": [\n [\"Kun Nong\", \"hosted event with\", \"Cloris Leachman\"],\n [\"Cloris (...TRUNCATED)	[[{"content":"Query: What are different ways of connecting Kun Nong and someone who was born in Des (...TRUNCATED)	[ 6625 ]	[ 0 ]	"<answer>{\n\"1\": [\n [\"Kun Nong\", \"collaborated\", \"Peter Bogdanovich\"],\n [\"Peter Bogdano(...TRUNCATED)	"<answer>\n{\n\"1\": [\n [\"Kun Nong\", \"collaborated\", \"Peter Bogdanovich\"],\n [\"Peter Bogda(...TRUNCATED)	[{"content":"Query: What are different ways of connecting Kun Nong and someone who was born in Des M(...TRUNCATED)	["<answer>{\n\"1\": [\n [\"Kun Nong\", \"collaborated\", \"Peter Bogdanovich\"],\n [\"Peter Bogdan(...TRUNCATED)	["Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nT(...TRUNCATED)	[ { "completion_tokens": 4461, "prompt_tokens": 2056, "total_tokens": 6517 } ]
[ "Q423327", "P2175", "Q12199" ]	[ "Q422654", "P2175", "Q12199" ]	[ "Q422654", "P769", "Q898407" ]	[ "enfuvirtide", "medical condition treated", "HIV/AIDS" ]	[ "saquinavir", "medical condition treated", "HIV/AIDS" ]	[ "saquinavir", "significant drug interaction", "venlafaxine" ]	Q12199__P2175	false	"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)	"What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a substance (...TRUNCATED)	enfuvirtide	venlafaxine	significant drug interaction	5	[{"content":"Query: What are different ways of connecting enfuvirtide, a medication used to treat HI(...TRUNCATED)	["<answer>\n{\n \"1\": [\n [\"enfuvirtide\", \"marketed as\", \"Fuzeon\"],\n [\"Fuzeon\", \"u(...TRUNCATED)	[[{"content":"Query: What are different ways of connecting enfuvirtide, a medication used to treat H(...TRUNCATED)	[ 7988 ]	[ 7040 ]	"<think>\nExploring drug interactions\n\nI need to trace various paths from 'enfuvirtide' to a f(...TRUNCATED)	"<answer>\n{\n \"1\": [\n [\"enfuvirtide\", \"approved by\", \"U.S. Food and Drug Administration(...TRUNCATED)	[{"content":"Query: What are different ways of connecting enfuvirtide, a medication used to treat HI(...TRUNCATED)	["<think>\nExploring drug interactions\n\nI need to trace various paths from 'enfuvirtide' to a (...TRUNCATED)	["Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a su(...TRUNCATED)	[ { "completion_tokens": 7981, "prompt_tokens": 1907, "total_tokens": 9888 } ]
[ "Q77462", "P463", "Q32645" ]	[ "Q95556", "P463", "Q32645" ]	[ "Q95556", "P451", "Q551050" ]	[ "Bela B", "member of", "Die Ärzte" ]	[ "Hagen Liebing", "member of", "Die Ärzte" ]	[ "Hagen Liebing", "unmarried partner", "Anja Caspary" ]	Q32645__P463	false	"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)	"What are different ways of connecting Bela B, the German musician, and someone who is the unmarried(...TRUNCATED)	Bela B	Anja Caspary	unmarried partner	6	[{"content":"Query: What are different ways of connecting Bela B, the German musician, and someone w(...TRUNCATED)	["<answer>\n{\n1: [\n [\"Bela B\", \"born in\", \"Spandau\"],\n [\"Spandau\", \"part of\", \"Berli(...TRUNCATED)	[[{"content":"Query: What are different ways of connecting Bela B, the German musician, and someone (...TRUNCATED)	[ 5279 ]	[ 4672 ]	"<think>\n\n</think>\n\n<answer>{\n1: [\n [\"Bela B\", \"bandmate of\", \"Hagen Liebing\"],\n [\"H(...TRUNCATED)	"<answer>\n{\n1: [\n [\"Bela B\", \"bandmate of\", \"Hagen Liebing\"],\n [\"Hagen Liebing\", \"unm(...TRUNCATED)	[{"content":"Query: What are different ways of connecting Bela B, the German musician, and someone w(...TRUNCATED)	["<think>\n\n</think>\n\n<answer>{\n1: [\n [\"Bela B\", \"bandmate of\", \"Hagen Liebing\"],\n [\"(...TRUNCATED)	["Query: What are different ways of connecting Bela B, the German musician, and someone who is the u(...TRUNCATED)	[ { "completion_tokens": 4264, "prompt_tokens": 1549, "total_tokens": 5813 } ]
[ "Q651253", "P40", "Q1268" ]	[ "Q9356382", "P40", "Q1268" ]	[ "Q9356382", "P22", "Q11716498" ]	[ "Nicolas Chopin", "child", "Frédéric Chopin" ]	[ "Tekla Justyna Chopin", "child", "Frédéric Chopin" ]	[ "Tekla Justyna Chopin", "father", "Jakub Krzyżanowski" ]	Q1268__P40	false	"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)	"What are different ways of connecting Nicolas Chopin, and someone who is the father of Jakub Krzyż(...TRUNCATED)	Nicolas Chopin	Jakub Krzyżanowski	father	7	[{"content":"Query: What are different ways of connecting Nicolas Chopin, and someone who is the fat(...TRUNCATED)	["<answer>\n{\n \"1\": [\n [\"Nicolas Chopin\", \"member of\", \"Warsaw Masonic Lodge\"],\n [(...TRUNCATED)	[[{"content":"Query: What are different ways of connecting Nicolas Chopin, and someone who is the fa(...TRUNCATED)	[ 6354 ]	[ 0 ]	"<answer>{\n \"1\": [\n [\"Nicolas Chopin\", \"father\", \"Jakub Krzyżanowski\"]\n ],\n \"2\"(...TRUNCATED)	"<answer>\n{\n \"1\": [\n [\"Nicolas Chopin\", \"father\", \"Jakub Krzyżanowski\"]\n ],\n \"2(...TRUNCATED)	[{"content":"Query: What are different ways of connecting Nicolas Chopin, and someone who is the fat(...TRUNCATED)	["<answer>{\n \"1\": [\n [\"Nicolas Chopin\", \"father\", \"Jakub Krzyżanowski\"]\n ],\n \"2\(...TRUNCATED)	["Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jaku(...TRUNCATED)	[ { "completion_tokens": 5612, "prompt_tokens": 2384, "total_tokens": 7996 } ]
[ "Q23505", "P40", "Q207" ]	[ "Q190628", "P40", "Q207" ]	[ "Q190628", "P39", "Q7166256" ]	[ "George H. W. Bush", "child", "George W. Bush" ]	[ "Barbara Bush", "child", "George W. Bush" ]	[ "Barbara Bush", "position held", "First Lady of the United States" ]	Q207__P40	false	"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)	"What are different ways of connecting George H. W. Bush, the 41st President of the United States, a(...TRUNCATED)	George H. W. Bush	First Lady of the United States	position held	8	[{"content":"Query: What are different ways of connecting George H. W. Bush, the 41st President of t(...TRUNCATED)	["<answer>\n{\n\"1\": [\n [\"George H. W. Bush\", \"held\", \"President of the United States\"],\n (...TRUNCATED)	[[{"content":"Query: What are different ways of connecting George H. W. Bush, the 41st President of (...TRUNCATED)	[ 9431 ]	[ 7872 ]	"<think>\nClarifying presidential succession\n\nI’m realizing that Ford succeeded Nixon in 197(...TRUNCATED)	"<answer>\n{\n\"1\": [\n [\"George H. W. Bush\", \"spouse\", \"Barbara Bush\"],\n [\"Barbara Bush\(...TRUNCATED)	[{"content":"Query: What are different ways of connecting George H. W. Bush, the 41st President of t(...TRUNCATED)	["<think>\nClarifying presidential succession\n\nI’m realizing that Ford succeeded Nixon in 19(...TRUNCATED)	["Query: What are different ways of connecting George H. W. Bush, the 41st President of the United S(...TRUNCATED)	[ { "completion_tokens": 7921, "prompt_tokens": 2530, "total_tokens": 10451 } ]
[ "Q18037778", "P2293", "Q131755" ]	[ "Q18046338", "P2293", "Q131755" ]	[ "Q18046338", "P5572", "Q64386" ]	[ "INTS7", "genetic association", "bipolar disorder" ]	[ "MCTP1", "genetic association", "bipolar disorder" ]	[ "MCTP1", "expressed in", "gallbladder" ]	Q131755__P2293	false	"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)	"What are different ways of connecting INTS7, a protein involved in various cellular processes, and (...TRUNCATED)	INTS7	gallbladder	expressed in	9	[{"content":"Query: What are different ways of connecting INTS7, a protein involved in various cellu(...TRUNCATED)	["<answer>\n{\n \"1\": [\n [\"INTS7\", \"member of\", \"Integrator complex\"],\n [\"Integrato(...TRUNCATED)	[[{"content":"Query: What are different ways of connecting INTS7, a protein involved in various cell(...TRUNCATED)	[ 4344 ]	[ 3648 ]	"<think>\nExploring expression relationships\n\nI’m working on connecting INTS7 to substances (...TRUNCATED)	"<answer>\n{\n \"1\": [\n [\"INTS7\", \"member of\", \"Integrator complex\"],\n [\"Integrator(...TRUNCATED)	[{"content":"Query: What are different ways of connecting INTS7, a protein involved in various cellu(...TRUNCATED)	["<think>\nExploring expression relationships\n\nI’m working on connecting INTS7 to substances(...TRUNCATED)	["Query: What are different ways of connecting INTS7, a protein involved in various cellular process(...TRUNCATED)	[ { "completion_tokens": 4780, "prompt_tokens": 1646, "total_tokens": 6426 } ]

End of preview. Expand in Data Studio

Dataset: connections-dev/connection_queries_jan12_natural_original_1_medium_0.7_4096_gpt-5-mini-2025-08-07_v2

This dataset was generated using the inference script with the following configuration:

Inference Parameters

Model Configuration

Model Name: gpt-5-mini-2025-08-07
Server URL: Not specified
API Key: Not provided
Request Timeout: 700 seconds

Query Configuration

Query Type: natural
Query Column: query
Sampling Type: iterate1

Generation Parameters

Temperature: 0.7
Max Tokens: 1024
Number of Runs: 1
Chunk Size: Entire dataset
Effort Level: medium

Feature Flags

Step by Step Reasoning: False
Reasoning Enabled: True
No Curator: False
Index Filter: None (all samples)
Start Index: None
End Index: None

Data Information

Input File: connections-dev/connection_queries_jan12_natural_original_1_medium_0.7_4096_gpt-5-mini-2025-08-07_v2
Number of Samples: 931
Output Filename: connection_queries_jan12__natural__iterate1__1__reasoning__medium__0.7__1024__gpt-5-mini-2025-08-07.jsonl

Dataset Structure

The dataset contains the following key columns:

query: The original query
entity_a: Starting entity
entity_b: Target entity
rel_b: Target relationship
path_prediction: Generated connection paths
prompt_for_path: Prompts used for path generation

Usage

You can load this dataset using:

from datasets import load_dataset

dataset = load_dataset("connections-dev/connection_queries_jan12_natural_iterate1_1_reason_medium_0.7_1024_gpt-5-mini-20")

Generation Details

This dataset was generated on 2026-01-26 00:06:02 using the inference pipeline with the above configuration.

Downloads last month: 7