Triple

T22014572
Position Surface form Disambiguated ID Type / Status
Subject Fanny and Elvis E543673 entity
Predicate castMember P1668 FINISHED
Object John Henshaw 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 Henshaw | Statement: [Fanny and Elvis, castMember, John Henshaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Henshaw
Context triple: [Fanny and Elvis, castMember, John Henshaw]
  • A. John Henshaw chosen
    John Henshaw is a British actor known for his character roles in film and television, including a prominent part in the Ken Loach-directed film "Looking for Eric."
  • B. Jere Henshaw
    Jere Henshaw is a film producer best known for his work on the 1987 teen romantic comedy "Can't Buy Me Love."
  • C. George Haines
    George Haines was a renowned American swimming coach best known for developing numerous Olympic champions and elevating U.S. competitive swimming in the mid-20th century.
  • D. Charles Hinshaw
    Charles Hinshaw is a writer best known for his work on the film "Needed Me."
  • E. William Harrigan
    William Harrigan was an American character actor of stage and screen, active in the early to mid-20th century, known for his supporting roles in crime and drama films.
  • 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_69e11e2db934819095556760c7d85e4d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127a6bf6081909865781ea7937a1b completed April 28, 2026, 9:33 p.m.
Created at: April 16, 2026, 8:22 p.m.