Triple

T17564979
Position Surface form Disambiguated ID Type / Status
Subject The Pagemaster E427786 entity
Predicate stars P1956 FINISHED
Object Mel Harris 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: Mel Harris | Statement: [The Pagemaster, stars, Mel Harris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mel Harris
Context triple: [The Pagemaster, stars, Mel Harris]
  • A. Mel Harris chosen
    Mel Harris is an American actress best known for her role as Hope Murdoch Steadman on the television drama series "Thirtysomething."
  • B. Ken Harris
    Ken Harris was a renowned American animator best known for his influential work on Warner Bros. cartoons, particularly in collaboration with director Chuck Jones.
  • C. Sean Harris
    Sean Harris is a British actor known for his intense character roles in film and television, including his portrayal of the android-hating geologist Fifield in the science fiction film "Prometheus."
  • D. Jack Harris
    Jack Harris is an actor known for his role in the film "Crashing Towers."
  • E. Keith Harris
    Keith Harris is an American record producer, songwriter, and multi-instrumentalist best known for his work with major pop and R&B artists such as the Black Eyed Peas.
  • 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4592ce42c8190a54a0a328c5e8ffc completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.