Triple

T20846421
Position Surface form Disambiguated ID Type / Status
Subject Derek Delevan Harris E513236 entity
Predicate spouse P13 FINISHED
Object Bo Derek 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: Bo Derek | Statement: [Derek Delevan Harris, spouse, Bo Derek]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bo Derek
Context triple: [Derek Delevan Harris, spouse, Bo Derek]
  • A. Bo Derek chosen
    Bo Derek is an American actress and model best known for her breakout role in the 1979 film "10," which made her a major sex symbol of the late 20th century.
  • B. Salman Khan
    Salman Khan is an American educator and entrepreneur best known as the founder of the online learning platform Khan Academy.
  • C. Salman Khan
    Salman Khan is a major Indian film actor and producer, known for his blockbuster Hindi movies, larger-than-life screen persona, and significant influence on Bollywood popular culture.
  • D. Sunny Deol
    Sunny Deol is an Indian film actor, director, and politician best known for his powerful action roles and intense performances in Hindi cinema.
  • E. Jeetendra
    Jeetendra is a veteran Indian film and television actor best known for his prolific work in Hindi cinema from the 1960s through the 1990s and his energetic dance-oriented roles.
  • 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_69e0b4f4898081908209e58edb8f9c45 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c34ffb588190881953a0480b29a8 completed April 21, 2026, 12:22 a.m.
Created at: April 16, 2026, 12:43 p.m.