Triple

T14925825
Position Surface form Disambiguated ID Type / Status
Subject Department of History (University of Wisconsin–Madison) E371630 entity
Predicate affiliation P10 FINISHED
Object College of Letters and Science (University of Wisconsin–Madison)
The College of Letters and Science at the University of Wisconsin–Madison is the university’s largest and most comprehensive academic division, encompassing a wide range of humanities, social sciences, natural sciences, and interdisciplinary programs.
E1141380 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: College of Letters and Science (University of Wisconsin–Madison) | Statement: [Department of History (University of Wisconsin–Madison), affiliation, College of Letters and Science (University of Wisconsin–Madison)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: College of Letters and Science (University of Wisconsin–Madison)
Context triple: [Department of History (University of Wisconsin–Madison), affiliation, College of Letters and Science (University of Wisconsin–Madison)]
  • A. University of Wisconsin–Madison
    The University of Wisconsin–Madison is a major public research university in Madison, Wisconsin, renowned for its strong academic programs, extensive research output, and flagship status within the University of Wisconsin System.
  • B. College of Agriculture at the University of Wisconsin–Madison
    The College of Agriculture at the University of Wisconsin–Madison is a leading academic and research institution specializing in agricultural and life sciences, known for its contributions to farming innovation, environmental stewardship, and food systems.
  • C. Board of Regents of the University of Wisconsin System
    The Board of Regents of the University of Wisconsin System is the governing body that oversees policy, administration, and strategic direction for the multi-campus University of Wisconsin System.
  • D. University of Wisconsin System
    The University of Wisconsin System is a large public university system in the United States that encompasses multiple campuses across Wisconsin and is known for its research, education, and public service.
  • E. College of Letters and Science
    The College of Letters and Science is UCLA’s largest academic division, encompassing a broad range of undergraduate and graduate programs in the humanities, social sciences, natural sciences, and interdisciplinary studies.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: College of Letters and Science (University of Wisconsin–Madison)
Triple: [Department of History (University of Wisconsin–Madison), affiliation, College of Letters and Science (University of Wisconsin–Madison)]
Generated description
The College of Letters and Science at the University of Wisconsin–Madison is the university’s largest and most comprehensive academic division, encompassing a wide range of humanities, social sciences, natural sciences, and interdisciplinary programs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: College of Letters and Science (University of Wisconsin–Madison)
Target entity description: The College of Letters and Science at the University of Wisconsin–Madison is the university’s largest and most comprehensive academic division, encompassing a wide range of humanities, social sciences, natural sciences, and interdisciplinary programs.
  • A. University of Wisconsin–Madison
    The University of Wisconsin–Madison is a major public research university in Madison, Wisconsin, renowned for its strong academic programs, extensive research output, and flagship status within the University of Wisconsin System.
  • B. College of Agriculture at the University of Wisconsin–Madison
    The College of Agriculture at the University of Wisconsin–Madison is a leading academic and research institution specializing in agricultural and life sciences, known for its contributions to farming innovation, environmental stewardship, and food systems.
  • C. Board of Regents of the University of Wisconsin System
    The Board of Regents of the University of Wisconsin System is the governing body that oversees policy, administration, and strategic direction for the multi-campus University of Wisconsin System.
  • D. University of Wisconsin System
    The University of Wisconsin System is a large public university system in the United States that encompasses multiple campuses across Wisconsin and is known for its research, education, and public service.
  • E. College of Letters and Science
    The College of Letters and Science is UCLA’s largest academic division, encompassing a broad range of undergraduate and graduate programs in the humanities, social sciences, natural sciences, and interdisciplinary studies.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d85cc7ea3481908228b5acb7d06f12 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded633da0c8190b39f606212e48e71 completed April 15, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69fec8741c048190b549782f49969f6a completed May 9, 2026, 5:39 a.m.
NEDg Description generation batch_69fec9d32f388190aef036dde9cdda42 completed May 9, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_69feca4a9db08190a083b5f0d9ec091b completed May 9, 2026, 5:46 a.m.
Created at: April 10, 2026, 2:35 a.m.