Triple

T19033375
Position Surface form Disambiguated ID Type / Status
Subject Promises, Promises (Broadway musical) E465800 entity
Predicate originalBroadwayStar P4737 FINISHED
Object Jill O'Hara 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: Jill O'Hara | Statement: [Promises, Promises (Broadway musical), originalBroadwayStar, Jill O'Hara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jill O'Hara
Context triple: [Promises, Promises (Broadway musical), originalBroadwayStar, Jill O'Hara]
  • A. Jill O'Hara chosen
    Jill O'Hara is an American actress and singer best known for her work on Broadway, including originating the role of Fran Kubelik in the musical "Promises, Promises."
  • B. Jenny O'Hara
    Jenny O'Hara is an American character actress known for her extensive work in film, television, and theater since the 1960s.
  • C. Jill Saint
    Jill Saint is the daughter of English novelist Dora Saint, better known by her pen name Miss Read, famed for her rural school and village stories.
  • D. Jill Knox
    Jill Knox is an artist and the wife of American actor and director Keith Powell.
  • E. Julie Dillon
    Julie Dillon is an American science fiction and fantasy illustrator renowned for her vibrant, imaginative digital artwork and multiple Hugo Award wins.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d741cabc8190900e12265ad269f8 completed April 20, 2026, 7:35 a.m.
Created at: April 10, 2026, 12:02 p.m.