Triple

T11814061
Position Surface form Disambiguated ID Type / Status
Subject George McRae E280951 entity
Predicate name P16 FINISHED
Object George McRae E280951 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: George McRae | Statement: [George McRae, name, George McRae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George McRae
Context triple: [George McRae, name, George McRae]
  • A. George McRae chosen
    George McRae was a Scottish-born Australian architect best known for designing prominent public buildings in Sydney, including the Queen Victoria Building.
  • B. Mel Sheppard
    Mel Sheppard was an American middle-distance runner and multiple Olympic gold medalist in the early 20th century.
  • C. Dick Emery
    Dick Emery was a popular English comedian and character actor best known for his long-running BBC television sketch show in the 1960s and 1970s.
  • D. Guy Mitchell
    Guy Mitchell was an American pop singer popular in the 1950s, known for his smooth vocal style and a string of chart-topping hits.
  • E. Brian Hyland
    Brian Hyland is an American pop singer best known for his 1960s novelty and teen pop hits such as "Itsy Bitsy Teenie Weenie Yellow Polka Dot Bikini."
  • 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_69d6ab26aae88190b2489efcb2a24234 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a5cba708819097467bb7aca7fc65 completed April 10, 2026, 7:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69f131a01aa48190bf5a70759ac886f6 completed April 28, 2026, 10:16 p.m.
Created at: April 8, 2026, 9:42 p.m.