Triple

T10089073
Position Surface form Disambiguated ID Type / Status
Subject Edna Best E215294 entity
Predicate spouse P13 FINISHED
Object Herbert Marshall E101443 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: Herbert Marshall | Statement: [Edna Best, spouse, Herbert Marshall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herbert Marshall
Context triple: [Edna Best, spouse, Herbert Marshall]
  • A. Herbert Marshall chosen
    Herbert Marshall was a distinguished English stage and film actor known for his suave, gentlemanly screen presence in classic Hollywood cinema of the 1930s and 1940s.
  • B. Leo Genn
    Leo Genn was a British actor and barrister known for his distinguished, authoritative screen presence in mid-20th-century films.
  • C. Arthur Coburn
    Arthur Coburn is a film editor best known for his work on major Hollywood productions, including the action-comedy classic "Beverly Hills Cop."
  • D. Arthur Coburn
    Arthur Coburn is a film editor best known for his work on the 1994 Jim Carrey comedy "The Mask."
  • E. Roy Boulting
    Roy Boulting was a British film director and producer, best known for the satirical and socially conscious films he made with his twin brother John Boulting from the 1940s to the 1970s.
  • 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_69ca83a1eed081908b2e9580f2ebeea7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd057e32881908bf630559af94906 completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d30050fbec8190ab7807d64ab73e61 completed April 6, 2026, 12:37 a.m.
Created at: March 30, 2026, 9:01 p.m.