Triple

T10523520
Position Surface form Disambiguated ID Type / Status
Subject Myrtle Gruenert E248234 entity
Predicate spouse P13 FINISHED
Object Lionel Logue E8696 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: Lionel Logue | Statement: [Myrtle Gruenert, spouse, Lionel Logue]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lionel Logue
Context triple: [Myrtle Gruenert, spouse, Lionel Logue]
  • A. Lionel Logue chosen
    Lionel Logue was an Australian speech therapist best known for helping King George VI overcome his stammer, as depicted in the film "The King’s Speech."
  • B. Ivor Slaney
    Ivor Slaney was a British composer and arranger known for his prolific work in film, television, and production music during the mid-20th century.
  • C. Roy Biggins
    Roy Biggins is a scheming, boorish rival airline owner and recurring antagonist on the sitcom "Wings."
  • D. Cecil Healy
    Cecil Healy was an Australian freestyle swimmer best known for winning a gold and silver medal at the 1912 Stockholm Olympics and for his notable sportsmanship in insisting a delayed rival be allowed to compete.
  • E. Chichester Bell
    Chichester Bell was an Irish chemist and inventor, best known for his work in acoustics and early sound recording technologies alongside Alexander Graham Bell.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509e155b08190996325bf484ec55d completed April 7, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e1c73208190aa3d3e30aa4482ac completed April 10, 2026, 2:50 p.m.
Created at: April 6, 2026, 12:29 p.m.