Triple

T21413478
Position Surface form Disambiguated ID Type / Status
Subject Philip Vanderpole E528236 entity
Predicate partOfCastWith P14987 FINISHED
Object Constance Cummings 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: Constance Cummings | Statement: [Philip Vanderpole, partOfCastWith, Constance Cummings]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Constance Cummings
Context triple: [Philip Vanderpole, partOfCastWith, Constance Cummings]
  • A. Constance Cummings chosen
    Constance Cummings was a British-American actress known for her work in 1930s Hollywood comedies and later acclaimed stage performances in the United Kingdom.
  • B. Constance Holt
    Constance Holt was the wife of British actor and film producer Edward Chapman.
  • C. Constance Clayton
    Constance Clayton is an American educator who became the first woman and first African American superintendent of the School District of Philadelphia.
  • D. Constance Dowling
    Constance Dowling was an American film and stage actress active in the 1940s and 1950s, known for her roles in Hollywood and Italian cinema.
  • E. Constance McCashin
    Constance McCashin is an American actress best known for her role as Laura Avery Sumner on the long-running prime-time soap opera "Knots Landing."
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b201ce1481908392c77e5ca40f5f completed April 22, 2026, 11:33 a.m.
Created at: April 16, 2026, 5:44 p.m.