Triple

T17838088
Position Surface form Disambiguated ID Type / Status
Subject Guillermo Brown E445445 entity
Predicate birthName P65 FINISHED
Object William Brown NE NERFINISHED

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: William Brown | Statement: [Guillermo Brown, birthName, William Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Brown
Context triple: [Guillermo Brown, birthName, William Brown]
  • A. William Brown
    William Brown was a civil engineer known for his role in the design and construction of the Severn Bridge in the United Kingdom.
  • B. William Brown
    William Brown was an American Revolutionary War soldier recognized as the first recipient of the Badge of Military Merit, a precursor to the modern Purple Heart.
  • C. William Brown chosen
    William Brown was an Irish-born admiral who became a national hero in Argentina as the founder and first commander of its navy.
  • D. William Brown
    William Brown is a civil engineer best known for designing Scotland’s Kessock Bridge, a prominent cable-stayed road bridge near Inverness.
  • E. William Brown
    William Brown was a civil engineer best known for designing Scotland’s Erskine Bridge, a major cable-stayed road bridge over the River Clyde.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f1a6d881909f024bc603111cdb completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48d29830c81909fa3ef5a352921b8 completed April 19, 2026, 8:07 a.m.
Created at: April 10, 2026, 10:16 a.m.