Triple

T14815463
Position Surface form Disambiguated ID Type / Status
Subject Constance Bennett E348300 entity
Predicate sibling P363 FINISHED
Object Barbara Bennett 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: Barbara Bennett | Statement: [Constance Bennett, sibling, Barbara Bennett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara Bennett
Context triple: [Constance Bennett, sibling, Barbara Bennett]
  • A. Barbara Bennett chosen
    Barbara Bennett was an American stage and film actress of the early 20th century, part of the prominent Bennett acting family.
  • B. Barbara Baker
    Barbara Baker is an Australian jurist and former judge who serves as the Governor of Tasmania.
  • C. Barbara Hopkinson
    Barbara Hopkinson is an author and grief recovery advocate known for helping individuals and families cope with the loss of loved ones.
  • D. Barbara Richardson
    Barbara Richardson is an American public figure best known as the longtime wife and partner of the late New Mexico governor and U.S. diplomat Bill Richardson, with whom she was active in civic and charitable causes.
  • E. Barbara Murray
    Barbara Murray was a British actress known for her extensive work in film and television, including prominent roles in mid-20th-century British dramas and series.
  • 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe0e89c81908c0e1fe2bc3ebcfc completed April 14, 2026, 11:38 p.m.
Created at: April 10, 2026, 1:49 a.m.