Triple

T14531321
Position Surface form Disambiguated ID Type / Status
Subject Rex Harrison E340920 entity
Predicate spouse P13 FINISHED
Object Rachel Roberts E524585 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: Rachel Roberts | Statement: [Rex Harrison, spouse, Rachel Roberts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rachel Roberts
Context triple: [Rex Harrison, spouse, Rachel Roberts]
  • A. Rachel Roberts chosen
    Rachel Roberts was a Welsh actress known for her intense, emotionally powerful performances in British and international films during the mid-20th century.
  • B. Rachel Roberts
    Rachel Roberts is a Canadian model and actress known for her work in fashion campaigns and films such as "Simone" and "Entourage."
  • C. Laura Roberts
    Laura Roberts is known primarily as the wife of American television and film composer Earle Hagen.
  • D. Kelly Roberts
    Kelly Roberts is a businesswoman best known for owning and overseeing the historic Mission Inn Hotel & Spa in Riverside, California.
  • E. Linda Steele
    Linda Steele is known as the wife of British speculative fiction author Michael Moorcock.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dea052d01c81909c8592c351be6f35 completed April 14, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde16666b8819090fb33c71515ab0a completed May 8, 2026, 1:13 p.m.
Created at: April 10, 2026, 1:22 a.m.