Triple

T19546861
Position Surface form Disambiguated ID Type / Status
Subject Ben Thompson E489088 entity
Predicate portrayedBy P1507 FINISHED
Object Zachary Scott 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: Zachary Scott | Statement: [Ben Thompson, portrayedBy, Zachary Scott]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zachary Scott
Context triple: [Ben Thompson, portrayedBy, Zachary Scott]
  • A. Zachary Scott chosen
    Zachary Scott was an American actor best known for his suave yet often villainous roles in 1940s and 1950s Hollywood films.
  • B. Robert Cummings
    Robert Cummings was an American film and television actor best known for his roles in comedies and thrillers during Hollywood’s Golden Age.
  • C. Dick Powell
    Dick Powell was an American actor, singer, and later film director and producer, known for his transition from light musical roles to hard-boiled film noir leads in the 1930s and 1940s.
  • D. Dana Andrews
    Dana Andrews was a prominent American film actor of the 1940s and 1950s, best known for his leading roles in classics such as "Laura" and "The Best Years of Our Lives."
  • E. Sterling Hayden
    Sterling Hayden was an American actor and World War II hero known for his rugged film roles and his clandestine service as a Marine and OSS operative.
  • 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.