Triple

T22021869
Position Surface form Disambiguated ID Type / Status
Subject The White Queen E543864 entity
Predicate executiveProducer P7225 FINISHED
Object John Griffin 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: John Griffin | Statement: [The White Queen, executiveProducer, John Griffin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Griffin
Context triple: [The White Queen, executiveProducer, John Griffin]
  • A. John Griffin
    John Griffin is a basketball coach best known for his tenure leading the Saint Joseph's Hawks men's basketball program.
  • B. John Griffin chosen
    John Griffin is a film and television producer known for his work on the historical drama series "The Devil’s Whore."
  • C. Kenyon M. Jordan
    Kenyon M. Jordan is the birth name of Buckshot, an American rapper best known as the frontman of the hip hop group Black Moon and co-founder of the Boot Camp Clik collective.
  • D. Leslie Edward Pridgen
    Leslie Edward Pridgen, better known by his stage name Freeway, is an American rapper from Philadelphia associated with Roc-A-Fella Records and the early 2000s East Coast hip hop scene.
  • E. James Allen McCune
    James Allen McCune is an American actor best known for his roles in the TV series "The Walking Dead" and the film "Blair Witch."
  • 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_69e11e2e8ea4819084210fe06d3a1b8d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127c8ac6881909a9e96e0873a3ae2 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:23 p.m.