Triple

T18726166
Position Surface form Disambiguated ID Type / Status
Subject University of Louisville Libraries E457904 entity
Predicate hasPart P35 FINISHED
Object Law Library NE NERFINISHED

How this triple was built (3 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: Law Library | Statement: [University of Louisville Libraries, hasPart, Law Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Law Library
Context triple: [University of Louisville Libraries, hasPart, Law Library]
  • A. Law Library
    The Law Library at UC Berkeley is a specialized academic library that supports legal research and education for students, faculty, and practitioners associated with the university’s law programs.
  • B. Law Library
    The Law Library at UNC-Chapel Hill is a specialized academic library that supports the university’s law school by providing comprehensive legal research resources, services, and study spaces for students, faculty, and legal scholars.
  • C. Law Library
    The Law Library is a specialized academic library focused on legal research materials and services, supporting the study and practice of law.
  • D. Law Library
    The Law Library at Victoria University of Wellington is a specialized academic library that supports legal education and research by providing access to comprehensive collections of law texts, journals, and legal resources.
  • E. Law Library
    The Law Library is a specialized branch of the University at Buffalo Libraries that provides legal research resources and services to support the study and practice of law.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Law Library
Target entity description: The Law Library at the University of Louisville is a specialized academic library that supports legal education and research for law students, faculty, and practitioners.
  • A. Law Library
    The Law Library is a specialized academic library focused on legal research materials and services, supporting the study and practice of law.
  • B. Law Library
    The Law Library at UC Berkeley is a specialized academic library that supports legal research and education for students, faculty, and practitioners associated with the university’s law programs.
  • C. Law Library
    The Law Library at Newcastle University is a specialized academic library that supports legal education and research by providing access to law books, journals, and online legal resources for students and faculty.
  • D. Law Library
    The Law Library at the University of the Witwatersrand is a specialized academic library that supports legal education and research by providing access to comprehensive collections of law books, journals, and legal resources.
  • E. Law Library
    The Law Library at Boston University is a specialized academic library that supports legal education and research for the university’s law school community.
  • F. None of above. chosen

Provenance (2 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d73f68c81908a9ddf2cc2fb9813 completed April 20, 2026, 12:04 a.m.
Created at: April 10, 2026, 11:50 a.m.