Triple

T4860742
Position Surface form Disambiguated ID Type / Status
Subject Great Hall (Hart House) E108651 entity
Predicate partOf P40 FINISHED
Object Hart House E19687 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: Hart House | Statement: [Great Hall (Hart House), partOf, Hart House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hart House
Context triple: [Great Hall (Hart House), partOf, Hart House]
  • A. Hart House chosen
    Hart House is a historic student activity and cultural centre at the University of Toronto’s St. George campus, known for its Gothic architecture and role as a hub for arts, debate, and recreation.
  • B. Wilf Hall
    Wilf Hall is an academic building at New York University School of Law that houses classrooms, faculty offices, and legal program facilities.
  • C. Hart Hall
    Hart Hall was a medieval academic hall at the University of Oxford that later evolved into what is now Hertford College.
  • D. Higgins Hall
    Higgins Hall is a prominent academic building at Pratt Institute’s Brooklyn campus, known especially for housing the School of Architecture and related design studios.
  • E. Higgins Hall
    Higgins Hall is an academic building on Boston College’s Chestnut Hill campus, primarily housing science classrooms, laboratories, and faculty offices.
  • 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_69bd440b965081908b0557721cae6338 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d5e247c8190b6ae4e9b529f0345 completed March 20, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5cf49590819084de6b655f1c8e88 completed March 21, 2026, 8:55 a.m.
Created at: March 20, 2026, 1:26 p.m.