Triple

T21872147
Position Surface form Disambiguated ID Type / Status
Subject Malcolm Harker E540031 entity
Predicate filmEditedByWork P129656 FINISHED
Object David Holden 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: David Holden | Statement: [Malcolm Harker, filmEditedByWork, David Holden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Holden
Context triple: [Malcolm Harker, filmEditedByWork, David Holden]
  • A. David Holden chosen
    David Holden is a film editor known for his work on the movie "The Warriors."
  • B. Max Holden
    Max Holden is a fictional character from the soap opera "One Life to Live," known for his complex romantic entanglements and dramatic storylines in Llanview.
  • C. Michael Matheson
    Michael Matheson is a Scottish National Party politician who has served as a Member of the Scottish Parliament and held several senior ministerial roles in the Scottish Government.
  • D. Arthur Holden
    Arthur Holden is a Canadian actor and voice actor best known for his work in animation, television, and video games.
  • E. David Roden
    David Roden is a British television writer best known for his work on the Doctor Who charity special "Dimensions in Time."
  • 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_69e0c478f59081909d54302b57fc1ce3 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0f3368d488190a37224b587858ab0 completed April 28, 2026, 5:49 p.m.
Created at: April 16, 2026, 6:59 p.m.