Triple

T17527336
Position Surface form Disambiguated ID Type / Status
Subject Normal Public Library E426832 entity
Predicate name P16 FINISHED
Object Normal Public 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: Normal Public Library | Statement: [Normal Public Library, name, Normal Public Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Normal Public Library
Context triple: [Normal Public Library, name, Normal Public Library]
  • A. Normal Public Library chosen
    Normal Public Library is the main public library serving the residents of Normal, Illinois with lending materials, community programs, and information services.
  • B. General Library
    General Library is the main central library of the University of Tokyo, serving as a primary hub for its academic and research collections.
  • C. Main Library
    Main Library is the principal academic library of the University of Dundee, providing core study spaces, resources, and services for its students and staff.
  • D. Main Library
    The Main Library is the principal academic library and study hub serving students and staff at the University of Birmingham.
  • E. Main Library
    The Main Library at Birzeit University is the institution’s central academic library, providing students and faculty with access to extensive print and digital research resources and study facilities.
  • 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_69d889de677081909b22d2657b1f0292 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e452d7523c819099278507e4a718d4 completed April 19, 2026, 3:58 a.m.
Created at: April 10, 2026, 5:49 a.m.