Triple

T15368730
Position Surface form Disambiguated ID Type / Status
Subject Deliver Us from Evil E367485 entity
Predicate castMember P1668 FINISHED
Object Sean Harris E270642 NE FINISHED

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: Sean Harris | Statement: [Deliver Us from Evil, castMember, Sean Harris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sean Harris
Context triple: [Deliver Us from Evil, castMember, Sean Harris]
  • A. Sean Harris chosen
    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."
  • B. Mel Harris
    Mel Harris is an American actress best known for her role as Hope Murdoch Steadman on the television drama series "Thirtysomething."
  • C. Craig Harris
    Craig Harris is an American jazz trombonist and composer known for his innovative work in avant-garde jazz and film scores, including the soundtrack for "Judas and the Black Messiah."
  • D. 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.
  • E. Keith Harris
    Keith Harris is a writer known for his contributions to the music and entertainment publication OMG.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e4b88a881909f9575c02aed287d completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82e1b698819098930596327340d7 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 3:18 a.m.