Triple

T3395952
Position Surface form Disambiguated ID Type / Status
Subject KeyCite E71528 entity
Predicate partOf P40 FINISHED
Object Westlaw E13650 NE FINISHED

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: Westlaw | Statement: [KeyCite, partOf, Westlaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Westlaw
Context triple: [KeyCite, partOf, Westlaw]
  • A. Westlaw chosen
    Westlaw is a comprehensive online legal research service and database widely used by lawyers, judges, and scholars to access case law, statutes, regulations, and secondary legal materials.
  • B. LexisNexis
    LexisNexis is a major legal research and information services provider offering extensive databases of case law, statutes, news, and business information to legal and professional users worldwide.
  • C. Bloomberg Law
    Bloomberg Law is a comprehensive legal research and business intelligence platform that provides access to case law, statutes, regulations, dockets, news, and analytical tools for legal professionals.
  • D. Legal Research Building
    The Legal Research Building is a prominent facility at the University of Michigan Law School that houses its law library and supports advanced legal scholarship.
  • E. 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.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad85a9c4a88190a854019341cb3b60 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb856158c81908dd7d3f1f8d6af74 completed March 8, 2026, 5:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bb7335ac81908b8e31dc7fb3d273 completed March 13, 2026, 7:23 a.m.
Created at: March 8, 2026, 3:14 p.m.