Triple

T15585
Position Surface form Disambiguated ID Type / Status
Subject Harvard Yard E310 entity
Predicate hasLandmark P105 FINISHED
Object Widener Library E8805 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: Widener Library | Statement: [Harvard Yard, hasLandmark, Widener Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Widener Library
Context triple: [Harvard Yard, hasLandmark, Widener Library]
  • A. Widener Library chosen
    Widener Library is Harvard University's principal humanities and social sciences library and one of the largest university libraries in the world.
  • B. Lamont Library
    Lamont Library is an undergraduate-focused library at Harvard University known for its extensive collections, study spaces, and late-night access.
  • C. Baker Library
    Baker Library is Harvard Business School’s principal library, renowned for its extensive collections in business and management and its iconic presence on the Boston campus.
  • D. Rotch Library
    Rotch Library is MIT’s primary library for architecture, planning, and art, housing specialized collections and resources that support research and education in these fields.
  • E. Hayden Library
    Hayden Library is the main humanities and science library at the Massachusetts Institute of Technology, serving as a central hub for research and study on campus.
  • 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_69a23d7ad88c8190bffe8ab091d86642 completed Feb. 28, 2026, 12:57 a.m.
NER Named-entity recognition batch_69a2400257208190b3cd87ad2a06c18f completed Feb. 28, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2b4b495c4819084ed1b661f1d0a24 completed Feb. 28, 2026, 9:26 a.m.
Created at: Feb. 28, 2026, 1:02 a.m.