Triple

T4063815
Position Surface form Disambiguated ID Type / Status
Subject The Wolfman (2010 film) E86277 entity
Predicate screenwriter P2831 FINISHED
Object David Self E308440 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: David Self | Statement: [The Wolfman (2010 film), screenwriter, David Self]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Self
Context triple: [The Wolfman (2010 film), screenwriter, David Self]
  • A. David Self chosen
    David Self is an American screenwriter known for his work on films such as "Road to Perdition" and other major Hollywood projects.
  • B. Don Self
    Don Self is a duplicitous Homeland Security agent in the TV series "Prison Break," known for recruiting Michael Scofield’s team before ultimately betraying them in season 4.
  • C. David Denman
    David Denman is an American actor best known for his role as Roy Anderson on the U.S. version of "The Office" and for supporting performances in films and television series across comedy and drama.
  • D. Andrew Laeddis
    Andrew Laeddis is the true identity of U.S. Marshal Teddy Daniels, revealed as a delusional patient in the psychological thriller "Shutter Island."
  • E. David Burrows
    David Burrows is a film editor best known for his work on major animated features, including The Lego Movie.
  • 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_69aed93c69208190a4efac0efe3cd69b completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbd7896c81909c61ed0d910d9c5f completed March 9, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562ae949c819092affaaca97c16d1 completed March 14, 2026, 1:29 p.m.
Created at: March 9, 2026, 3:38 p.m.