Triple

T18826310
Position Surface form Disambiguated ID Type / Status
Subject The Count E460395 entity
Predicate featuresActor P15562 FINISHED
Object Leo White 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: Leo White | Statement: [The Count, featuresActor, Leo White]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leo White
Context triple: [The Count, featuresActor, Leo White]
  • A. Leo White chosen
    Leo White was a British-born American character actor and director best known for his work in silent films, including frequent collaborations with Charlie Chaplin.
  • B. Bibb Falk
    Bibb Falk was an American baseball player and longtime University of Texas coach known for leading the Longhorns to multiple national championships and having the school's baseball stadium named in his honor.
  • C. Gil Doud
    Gil Doud was an American screenwriter best known for his work on mid-20th-century Hollywood films, particularly war and action dramas.
  • D. David Kaye
    David Kaye is a Canadian voice actor best known for his extensive work in animation and video games, including major roles in the Transformers franchise.
  • E. Hans Conried
    Hans Conried was an American character actor and voice actor best known for his comedic and often villainous roles in mid-20th-century film, radio, television, and animation.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6bec7b08190b040ec8b3693f037 completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:56 a.m.