Triple

T7471860
Position Surface form Disambiguated ID Type / Status
Subject Crawford E176525 entity
Predicate hasNotableBearer P458 FINISHED
Object Cindy Crawford E455512 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: Cindy Crawford | Statement: [Crawford, hasNotableBearer, Cindy Crawford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cindy Crawford
Context triple: [Crawford, hasNotableBearer, Cindy Crawford]
  • A. Cindy Crawford chosen
    Cindy Crawford is an American supermodel and actress who rose to international fame in the late 1980s and 1990s and became one of the most recognizable fashion icons in the world.
  • B. Christie Brinkley
    Christie Brinkley is an American model and actress best known for her long-running prominence in fashion and cosmetics advertising, including iconic work in the 1970s and 1980s.
  • C. Patricia Bündchen
    Patricia Bündchen is the fraternal twin sister of Brazilian supermodel Gisele Bündchen, known for working closely with her as a manager and business partner.
  • D. Heather Graham
    Heather Graham is an American actress known for her roles in films such as "Boogie Nights," "Austin Powers: The Spy Who Shagged Me," and "The Hangover."
  • E. Lola Ray Facinelli
    Lola Ray Facinelli is the daughter of American actor Peter Facinelli.
  • 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_69c69f223fd88190b4c69b95d7cbeeda completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f415b5cc81909e1e097c90f460b6 completed March 27, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83480a40c8190a7ae3e08022735a1 completed March 28, 2026, 8:05 p.m.
Created at: March 27, 2026, 3:41 p.m.