Triple

T11121465
Position Surface form Disambiguated ID Type / Status
Subject Joan Rivers E263026 entity
Predicate stageName P7872 FINISHED
Object Joan Rivers E263026 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: Joan Rivers | Statement: [Joan Rivers, stageName, Joan Rivers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan Rivers
Context triple: [Joan Rivers, stageName, Joan Rivers]
  • A. Joan Rivers chosen
    Joan Rivers was a pioneering American stand-up comedian and television personality known for her acerbic wit, trailblazing work for women in comedy, and sharp-tongued red carpet commentary.
  • B. Ginny Newhart
    Ginny Newhart was an American homemaker and the longtime wife of comedian and actor Bob Newhart, known for her behind-the-scenes influence on his career and for inspiring key ideas in his television work.
  • C. Betty DeGeneres
    Betty DeGeneres is an American LGBTQ+ rights advocate and author best known as the mother of comedian and television host Ellen DeGeneres.
  • D. Mavis Leno
    Mavis Leno is an American feminist and philanthropist known for her long-time activism, particularly in advocating for women's rights in Afghanistan.
  • E. Kathy Griffin
    Kathy Griffin is an American stand-up comedian and actress known for her sharp, often controversial humor and frequent television appearances.
  • 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_69d6aa9b46cc8190b19f9f0cc45bf322 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79af911b881908168f23a4918231c completed April 9, 2026, 12:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69e42d8406988190837a16d7ad8048d1 completed April 19, 2026, 1:19 a.m.
Created at: April 8, 2026, 9:28 p.m.