Triple

T11195042
Position Surface form Disambiguated ID Type / Status
Subject Princess Yasmin Aga Khan E264900 entity
Predicate sibling P363 FINISHED
Object Rebecca Welles E260204 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: Rebecca Welles | Statement: [Princess Yasmin Aga Khan, sibling, Rebecca Welles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rebecca Welles
Context triple: [Princess Yasmin Aga Khan, sibling, Rebecca Welles]
  • A. Rebecca Welles chosen
    Rebecca Welles was the daughter of legendary film stars Rita Hayworth and Orson Welles.
  • B. James Dearden
    James Dearden is a British screenwriter and director best known for writing the screenplay for the hit psychological thriller film "Fatal Attraction."
  • C. Cecilia DeMille Harper
    Cecilia DeMille Harper was the daughter of legendary American film director and producer Cecil B. DeMille.
  • D. Virginia Welles
    Virginia Welles was an American film actress active in the 1940s and 1950s, known for her supporting roles in Hollywood dramas and comedies.
  • E. Angelica Garnett
    Angelica Garnett was a British writer and artist associated with the Bloomsbury Group, known for her memoirs about her unconventional upbringing among its members.
  • 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_69d6aa9eb9248190b20211772621b4bc completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8bf14e481908563b15790af4d20 completed April 9, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4840640688190a5b3c36883b8fce8 completed April 19, 2026, 7:28 a.m.
Created at: April 8, 2026, 9:29 p.m.