Triple

T18741721
Position Surface form Disambiguated ID Type / Status
Subject Darol Anger E458305 entity
Predicate collaboratedWith P435 FINISHED
Object Barbara Higbie 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: Barbara Higbie | Statement: [Darol Anger, collaboratedWith, Barbara Higbie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara Higbie
Context triple: [Darol Anger, collaboratedWith, Barbara Higbie]
  • A. Barbara Higbie chosen
    Barbara Higbie is an American pianist, violinist, singer-songwriter, and composer known for her genre-blending contemporary instrumental and folk-influenced music.
  • B. Elizabeth Cobb
    Elizabeth Cobb was the daughter of American humorist and author Irvin S. Cobb.
  • C. Mary Meredith
    Mary Meredith is a fictional character from the 1858 comedic play "Our American Cousin," which is best known as the play being performed at Ford's Theatre when President Abraham Lincoln was assassinated.
  • D. Geraldine Laybourne
    Geraldine Laybourne is an American media executive best known for her pioneering leadership at Nickelodeon and for co-founding and leading the women-focused cable network Oxygen.
  • E. Mary Dixon
    Mary Dixon is a fictional character from the long-running British television police drama "Dixon of Dock Green."
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5768ecc2081908143310190ffb460 completed April 20, 2026, 12:42 a.m.
Created at: April 10, 2026, 11:51 a.m.