Triple

T5334378
Position Surface form Disambiguated ID Type / Status
Subject John Derek E123789 entity
Predicate spouse P13 FINISHED
Object Ursula Andress E113885 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: Ursula Andress | Statement: [John Derek, spouse, Ursula Andress]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ursula Andress
Context triple: [John Derek, spouse, Ursula Andress]
  • A. Ursula Andress chosen
    Ursula Andress is a Swiss actress best known as the iconic first Bond girl, Honey Ryder, in the James Bond film "Dr. No."
  • B. Jill St. John
    Jill St. John is an American actress best known for playing Bond girl Tiffany Case in the James Bond film "Diamonds Are Forever."
  • C. Anita Ekberg
    Anita Ekberg was a Swedish actress and former model best known for her iconic role in Federico Fellini’s film "La Dolce Vita."
  • D. Aimee Boorman
    Aimee Boorman is an American gymnastics coach best known for guiding Simone Biles through her rise to becoming one of the most decorated gymnasts in history.
  • E. Lara Pulver
    Lara Pulver is a British actress known for her roles in television series such as "Sherlock" and "Spooks," as well as various film and stage productions.
  • 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_69bd464b07f8819095aa76577c9829e4 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85ae52c08190968a5567b7e6b794 completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf18baeca081909acc11d0c6c89f6d completed March 21, 2026, 10:16 p.m.
Created at: March 20, 2026, 2 p.m.