Triple

T20288504
Position Surface form Disambiguated ID Type / Status
Subject George Keister E509953 entity
Predicate notableWork P4 FINISHED
Object Belasco Theatre 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: Belasco Theatre | Statement: [George Keister, notableWork, Belasco Theatre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Belasco Theatre
Context triple: [George Keister, notableWork, Belasco Theatre]
  • A. Belasco Theatre chosen
    The Belasco Theatre is a historic Broadway playhouse in New York City renowned for its early 20th-century architecture and long-running theatrical productions.
  • B. Cort Theatre
    The Cort Theatre is a historic Broadway theater in New York City known for hosting major plays and productions since the early 20th century.
  • C. Delacorte Theater
    The Delacorte Theater is an open-air venue in New York City best known for hosting the Public Theater’s free Shakespeare in the Park productions each summer.
  • D. Hayes Theater
    Hayes Theater is a historic Broadway playhouse in New York City known for hosting contemporary and innovative theatrical productions.
  • E. Morosco Theatre
    Morosco Theatre was a prominent Broadway playhouse in New York City, best known for hosting major 20th-century productions including the original run of Arthur Miller’s "Death of a Salesman."
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6769414488190b38e07fd1e989aba completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 11:10 a.m.