Triple

T23074933
Position Surface form Disambiguated ID Type / Status
Subject Sherlock Holmes (1922 film) E575301 entity
Predicate cinematographyBy P1953 FINISHED
Object J. Roy Hunt 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: J. Roy Hunt | Statement: [Sherlock Holmes (1922 film), cinematographyBy, J. Roy Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: J. Roy Hunt
Context triple: [Sherlock Holmes (1922 film), cinematographyBy, J. Roy Hunt]
  • A. J. Roy Hunt chosen
    J. Roy Hunt was an American cinematographer known for his work during Hollywood’s early sound era, contributing to numerous notable films across several decades.
  • B. Robert Gordon Hunt
    Robert Gordon Hunt is known as the husband of American actress and singer Margaret Avery.
  • C. George Hunt
    George Hunt was an ethnologist and linguist best known for his extensive documentation of Kwakwaka'wakw culture and the Kwakʼwala language in collaboration with anthropologist Franz Boas.
  • D. William Herbert Hunt
    William Herbert Hunt is an American oil billionaire and member of the prominent Hunt family, known for his major role in the 1980 silver market speculation.
  • E. John L. Lumley
    John L. Lumley was a prominent American fluid dynamicist known for his pioneering contributions to the understanding and modeling of turbulence.
  • 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_69e245be28d48190ad1348d5a73db37d completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c62c200819099c92654493288ad completed April 29, 2026, 4:43 a.m.
Created at: April 17, 2026, 3:56 p.m.