Triple

T18387267
Position Surface form Disambiguated ID Type / Status
Subject Caged E446623 entity
Predicate screenwriter P2831 FINISHED
Object Virginia Kellogg 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: Virginia Kellogg | Statement: [Caged, screenwriter, Virginia Kellogg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Virginia Kellogg
Context triple: [Caged, screenwriter, Virginia Kellogg]
  • A. Virginia Kellogg chosen
    Virginia Kellogg was an American screenwriter best known for her hard-hitting crime and prison dramas in mid-20th-century Hollywood.
  • B. Virginia DuBridge
    Virginia DuBridge was the wife of American physicist and educator Lee A. DuBridge, who served as president of Caltech and science advisor to U.S. presidents.
  • C. Margaret Metcalfe
    Margaret Metcalfe was the mother of famed English comic actor and filmmaker Stan Laurel, one half of the legendary comedy duo Laurel and Hardy.
  • D. Mildred McAfee Horton
    Mildred McAfee Horton was an American educator and naval officer who became the first director of the U.S. Navy’s WAVES program and the first woman commissioned as a line officer in the U.S. Navy.
  • E. Frances Minturn Howard
    Frances Minturn Howard was an American poet and author known for her mid-20th-century verse and contributions to literary magazines.
  • 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_69d8b9f370b88190b1e5081c2c238e7f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e517a114c08190af1be1ae52c83b63 completed April 19, 2026, 5:57 p.m.
Created at: April 10, 2026, 10:46 a.m.