Triple

T5482467
Position Surface form Disambiguated ID Type / Status
Subject O'Brien E123498 entity
Predicate hasVariant P455 FINISHED
Object Bryan E186599 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: Bryan | Statement: [O'Brien, hasVariant, Bryan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bryan
Context triple: [O'Brien, hasVariant, Bryan]
  • A. Bryan
    Bryan is a mid-sized city in Central Texas known for its close association with neighboring College Station and Texas A&M University.
  • B. Bryan chosen
    Bryan is a masculine given name of Celtic origin that is widely used in English-speaking countries.
  • C. Bryse
    Bryse is an alternative spelling of the given name Bryce, typically used as a modern or stylistic variant.
  • D. Bryan Unkeless
    Bryan Unkeless is a film producer known for working on acclaimed movies such as "I, Tonya" and other high-profile Hollywood projects.
  • E. Bryan Burk
    Bryan Burk is an American film and television producer best known for his collaborations with J.J. Abrams on projects such as Lost, Star Trek, and Mission: Impossible.
  • 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_69bd4648883481909e9775d43300c5fa completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd924bac088190b7d08df91534b0bc completed March 20, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf6c812d4c8190a22f76b787ab0f10 completed March 22, 2026, 4:13 a.m.
Created at: March 20, 2026, 2:09 p.m.