Triple

T18007970
Position Surface form Disambiguated ID Type / Status
Subject The Sultan E430803 entity
Predicate voiceActor P1507 FINISHED
Object Douglas Seale 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: Douglas Seale | Statement: [The Sultan, voiceActor, Douglas Seale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Douglas Seale
Context triple: [The Sultan, voiceActor, Douglas Seale]
  • A. Douglas Seale chosen
    Douglas Seale was a British actor and voice artist known for his character roles in film, television, and animation, including work with Disney.
  • B. Douglas Pike
    Douglas Pike was a prominent American diplomat and scholar known for his influential analyses of the Viet Cong and the Vietnam War.
  • C. Richard Oakes
    Richard Oakes was a Mohawk Native American activist best known for helping lead the 1969–1971 occupation of Alcatraz Island, a landmark protest in the Red Power movement.
  • D. Allen M. Davey
    Allen M. Davey was an American cinematographer known for his work on early Technicolor films in Hollywood.
  • E. John Sewell
    John Sewell is a former English footballer and manager best known for his involvement in North American soccer, including coaching in the NASL.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b51d44088190bfcd35e532a4c02a completed April 19, 2026, 10:57 a.m.
Created at: April 10, 2026, 10:24 a.m.