Triple

T20570185
Position Surface form Disambiguated ID Type / Status
Subject Billy Getty E505073 entity
Predicate spouse P13 FINISHED
Object Vanessa Getty 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: Vanessa Getty | Statement: [Billy Getty, spouse, Vanessa Getty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vanessa Getty
Context triple: [Billy Getty, spouse, Vanessa Getty]
  • A. Vanessa Getty chosen
    Vanessa Getty is a San Francisco–based philanthropist and socialite known for her involvement in charitable causes and the fashion and arts communities.
  • B. Gisele MacKenzie
    Gisele MacKenzie was a Canadian singer and television personality best known for her popular vocal performances in the 1950s, including several hit recordings and frequent appearances on variety shows.
  • C. Vanessa Vadim
    Vanessa Vadim is a French-American filmmaker and environmental activist, best known as the daughter of actress Jane Fonda and director Roger Vadim.
  • D. Vanessa Angel
    Vanessa Angel is an English actress and former model best known for her roles in the film "Kingpin" and the TV series "Weird Science."
  • E. Linda Evangelista
    Linda Evangelista is a Canadian supermodel renowned as one of the most prominent faces of the 1990s fashion industry and a key member of the original “supermodel” era.
  • 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_69e0b4b721588190993ac7b0a9be2736 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a5b0688190b45d0fa993c4765c completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.