Triple

T13515739
Position Surface form Disambiguated ID Type / Status
Subject Edith Pretty E322753 entity
Predicate employed P7 FINISHED
Object Basil Brown E322754 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: Basil Brown | Statement: [Edith Pretty, employed, Basil Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Basil Brown
Context triple: [Edith Pretty, employed, Basil Brown]
  • A. Basil Brown chosen
    Basil Brown is a self-taught English archaeologist and astronomer best known for excavating the Sutton Hoo ship burial in 1939.
  • B. Francis Henry Brown
    Francis Henry Brown was a 19th-century American physician best known for his pioneering role in establishing pediatric care in Boston, including helping to found Boston Children’s Hospital.
  • C. Reginald Barker
    Reginald Barker was an early 20th-century American film director known for his work during the silent era.
  • D. James Searle Dawley
    James Searle Dawley was an early American film director, screenwriter, and producer best known for his pioneering work in silent cinema during the 1910s.
  • E. Arthur Whitten Brown
    Arthur Whitten Brown was a British aviator best known as the navigator on the first non-stop transatlantic flight in 1919 alongside pilot John Alcock.
  • 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_69d80766a21881909f21a1b7421d3b8a completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafa0ed508190b2855171b1945e84 completed April 12, 2026, 2:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75494642881909f33962afe26f427 completed May 3, 2026, 1:58 p.m.
Created at: April 9, 2026, 9:44 p.m.