Triple

T16497132
Position Surface form Disambiguated ID Type / Status
Subject Prince Igor Troubetzkoy E400712 entity
Predicate spouse P13 FINISHED
Object Barbara Hutton E93284 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: Barbara Hutton | Statement: [Prince Igor Troubetzkoy, spouse, Barbara Hutton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara Hutton
Context triple: [Prince Igor Troubetzkoy, spouse, Barbara Hutton]
  • A. Barbara Hutton chosen
    Barbara Hutton was an American socialite and Woolworth heiress famed for her immense fortune, lavish lifestyle, and highly publicized series of marriages and personal tragedies.
  • B. Leigh Douglas
    Leigh Douglas was the wife of former U.S. Secretary of State Warren Christopher.
  • C. Gloria Vanderbilt
    Gloria Vanderbilt was an American artist, socialite, fashion designer, and heiress renowned for her influential designer jeans line and prominent role in 20th-century high society.
  • D. Carole Landis
    Carole Landis was an American film actress and World War II pin-up star known for her glamorous screen presence in 1940s Hollywood.
  • E. Consuelo De Haviland
    Consuelo De Haviland is a French actress known for her supporting roles in European cinema, including appearances in cult films of the 1980s.
  • 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_69d88381f6148190819958a038be990e completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e343a7c81909e04cbaaa40e2531 completed April 18, 2026, 7:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0091872e648190b805aa4e41bcbb6d completed May 10, 2026, 2:09 p.m.
Created at: April 10, 2026, 5:14 a.m.