Triple

T22640774
Position Surface form Disambiguated ID Type / Status
Subject Liza Snyder E558817 entity
Predicate mother P120 FINISHED
Object Barbara Green 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 Green | Statement: [Liza Snyder, mother, Barbara Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara Green
Context triple: [Liza Snyder, mother, Barbara Green]
  • A. Barbara Green chosen
    Barbara Green is an individual associated with the Green family, known primarily as one of its members.
  • B. Sandra Green
    Sandra Green is a recurring character on the television series "Friends," known as Rachel Green’s somewhat overbearing and image-conscious mother.
  • C. Sally Greenberg
    Sally Greenberg is a consumer rights advocate and attorney who serves as a leading executive of the National Consumers League, focusing on protecting and promoting consumer interests.
  • D. Gillian Greene
    Gillian Greene is an American actress and filmmaker, known for her work in film and television and for being married to director Sam Raimi.
  • E. Elaine Barrish
    Elaine Barrish is a fictional former First Lady and Secretary of State who navigates political and family turmoil in the television miniseries "Political Animals."
  • 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_69e24547f7fc819086e2c4ba3b979657 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f170116fe881908178cffef26e3ae7 completed April 29, 2026, 2:42 a.m.
Created at: April 17, 2026, 3:04 p.m.