Triple

T14815465
Position Surface form Disambiguated ID Type / Status
Subject Constance Bennett E348300 entity
Predicate spouse P13 FINISHED
Object Gilbert Roland E382609 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: Gilbert Roland | Statement: [Constance Bennett, spouse, Gilbert Roland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gilbert Roland
Context triple: [Constance Bennett, spouse, Gilbert Roland]
  • A. Gilbert Roland chosen
    Gilbert Roland was a Mexican-born American actor known for his suave leading-man roles in silent and sound films, including numerous Westerns and adventure movies across a career spanning over six decades.
  • B. Hugh Sothern
    Hugh Sothern was an American character actor active in early 20th-century stage and film, known for supporting roles in Hollywood movies.
  • C. John Wesley Hoyt
    John Wesley Hoyt was an American politician and educator who served as the third Governor of the Wyoming Territory in the late 19th century.
  • D. Edmund Lowe
    Edmund Lowe was an American film actor best known for his leading roles in silent and early sound-era Hollywood films, particularly in war dramas and comedies.
  • E. Charles Bickford
    Charles Bickford was an American character actor known for his rugged screen presence and acclaimed supporting roles in numerous classic Hollywood films.
  • 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe0e89c81908c0e1fe2bc3ebcfc completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa929b0b88190ad40d54ba4ef478a completed May 9, 2026, 9:37 p.m.
Created at: April 10, 2026, 1:49 a.m.