Triple

T512518
Position Surface form Disambiguated ID Type / Status
Subject Baker Library E10637 entity
Predicate name P16 FINISHED
Object Baker Library E10637 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: Baker Library | Statement: [Baker Library, name, Baker Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Baker Library
Context triple: [Baker Library, name, Baker Library]
  • A. Baker Library chosen
    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.
  • B. Brooks Library
    Brooks Library is an academic library that serves the students and staff of Manchester Metropolitan University, providing access to scholarly resources and study facilities.
  • C. Stauffer Library
    Stauffer Library is the main research and academic library at Queen's University in Kingston, Ontario, serving as a central hub for student study, resources, and scholarly work.
  • D. Perkins Library
    Perkins Library is the main academic library at Duke University, serving as a central hub for research, study, and access to the university’s collections and resources.
  • E. Lamont Library
    Lamont Library is an undergraduate-focused library at Harvard University known for its extensive collections, study spaces, and late-night access.
  • 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_69a2e84a0d08819087e01863fcd9abf1 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f1804e908190a1d34ac952e84a3f completed Feb. 28, 2026, 1:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4a42a4a648190a1a01d823b698ae3 completed March 1, 2026, 8:40 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.