Triple

T19547448
Position Surface form Disambiguated ID Type / Status
Subject The Killing (1956 film) E489110 entity
Predicate castMember P1668 FINISHED
Object Ted de Corsia 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: Ted de Corsia | Statement: [The Killing (1956 film), castMember, Ted de Corsia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ted de Corsia
Context triple: [The Killing (1956 film), castMember, Ted de Corsia]
  • A. Ted de Corsia chosen
    Ted de Corsia was an American character actor known for his tough-guy roles in classic film noir and crime movies of the mid-20th century.
  • B. Joe Corallo
    Joe Corallo is a comic book writer and editor known for his work on independent and genre titles in the modern comics scene.
  • C. Greg Corrado
    Greg Corrado is an American computer scientist and researcher known for his pioneering work in artificial intelligence and deep learning, including co-founding Google Brain.
  • D. George Corsillo
    George Corsillo is a graphic designer and illustrator known for his distinctive book cover artwork, including the cover for Elmore Leonard’s novel "Maximum Bob."
  • E. Christian Corrao
    Christian Corrao is a voice actor known for his role in the animated film "PAW Patrol: The Mighty Movie."
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d2d8a6081908e9bb3a6f5d85896 completed April 20, 2026, 2:50 p.m.
Created at: April 10, 2026, 1:41 p.m.