Triple

T18950337
Position Surface form Disambiguated ID Type / Status
Subject Heafey Law Library E463629 entity
Predicate name P16 FINISHED
Object Heafey Law Library NE NERFINISHED

How this triple was built (2 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: Heafey Law Library | Statement: [Heafey Law Library, name, Heafey Law Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heafey Law Library
Context triple: [Heafey Law Library, name, Heafey Law Library]
  • A. Heafey Law Library chosen
    Heafey Law Library is the primary legal research library serving students and faculty at Santa Clara University School of Law.
  • B. Goodson Law Library
    Goodson Law Library is Duke University’s primary law library, supporting the research and educational needs of Duke Law School students, faculty, and scholars.
  • C. Robert Crown Law Library
    Robert Crown Law Library is the primary academic law library serving Stanford Law School, providing extensive legal research resources and services to students, faculty, and scholars.
  • D. Pardee Legal Research Center
    Pardee Legal Research Center is the main law library and research hub serving the University of San Diego School of Law’s students, faculty, and legal scholars.
  • E. Fineman and Pappas Law Libraries
    Fineman and Pappas Law Libraries is Boston University’s specialized law library system supporting the School of Law with comprehensive legal research resources and services.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d542b238819089ccd2df279a2f7f completed April 20, 2026, 7:26 a.m.
Created at: April 10, 2026, noon