Triple

T20388810
Position Surface form Disambiguated ID Type / Status
Subject The Other Woman E498029 entity
Predicate castMember P1668 FINISHED
Object Kate Upton 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: Kate Upton | Statement: [The Other Woman, castMember, Kate Upton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Upton
Context triple: [The Other Woman, castMember, Kate Upton]
  • A. Kate Upton chosen
    Kate Upton is an American model and actress best known for her appearances on the cover of the Sports Illustrated Swimsuit Issue and her work in film and fashion campaigns.
  • B. Kristen Olsen
    Kristen Olsen is an actress known for playing the character Hope Williams Brady on the long-running soap opera "Days of Our Lives."
  • C. Amber Valletta
    Amber Valletta is an American fashion model and actress known for her work in high-profile fashion campaigns and roles in films such as "Hitch" and "What Lies Beneath."
  • D. Ashley Graham
    Ashley Graham is the U.S. President’s kidnapped daughter whom Leon S. Kennedy must rescue in the survival horror video game Resident Evil 4.
  • E. Emily Ratajkowski
    Emily Ratajkowski is an American model and actress known for her breakout role in the thriller film "Gone Girl" and her prominent presence in fashion and popular culture.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790d9e5881908bde7da9e5e541a0 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.