Triple

T23017992
Position Surface form Disambiguated ID Type / Status
Subject The Woman in Green E573084 entity
Predicate starring P1507 FINISHED
Object Henry Daniell 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: Henry Daniell | Statement: [The Woman in Green, starring, Henry Daniell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henry Daniell
Context triple: [The Woman in Green, starring, Henry Daniell]
  • A. Henry Daniell chosen
    Henry Daniell was a British character actor renowned for his many villainous and aristocratic roles in classic Hollywood films of the 1930s and 1940s.
  • B. Charles Dobell
    Charles Dobell was a Canadian-born British Army general noted for his service in colonial campaigns and the First World War, particularly in the Middle Eastern theatre.
  • C. George Davison
    George Davison is an Anglican bishop who serves as a senior cleric in the Church of Ireland.
  • D. Edward Walson
    Edward Walson is a film producer known for working on projects such as Woody Allen’s romantic comedy "Magic in the Moonlight."
  • E. Charles Henry Daniel
    Charles Henry Daniel is the birth name of Henry Daniell, a British actor known for his refined villainous roles in classic Hollywood 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e64a4c8190b8d29ed638c7fef8 completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.