Triple

T15747950
Position Surface form Disambiguated ID Type / Status
Subject Robert Fuller E381766 entity
Predicate workedWith P398 FINISHED
Object Julie London E346769 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: Julie London | Statement: [Robert Fuller, workedWith, Julie London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julie London
Context triple: [Robert Fuller, workedWith, Julie London]
  • A. Julie London chosen
    Julie London was an American singer and actress renowned for her sultry, intimate vocal style and popular recordings in the 1950s and 1960s.
  • B. Jo Stafford
    Jo Stafford was an American traditional pop and jazz singer renowned for her smooth vocal style and numerous hit recordings from the 1940s through the 1950s.
  • C. Eydie Gormé
    Eydie Gormé was an American pop and Latin-influenced singer best known for her solo hits and her longtime musical partnership with her husband, Steve Lawrence.
  • D. Myrtle Reeves
    Myrtle Reeves was the first wife of American comic actor Oliver Hardy, known primarily for her connection to the famed Laurel and Hardy star.
  • E. Peggy Lee
    Peggy Lee was an acclaimed American jazz and popular music singer, songwriter, and actress known for her sultry voice and sophisticated, understated style.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0502d72008190b4d13a6b3a12e467 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffb03539c081908b5df46bb810b949 completed May 9, 2026, 10:07 p.m.
Created at: April 10, 2026, 4:46 a.m.