Triple

T11378213
Position Surface form Disambiguated ID Type / Status
Subject Brian O'Conner E269523 entity
Predicate closeFriend P8712 FINISHED
Object Roman Pearce E241105 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: Roman Pearce | Statement: [Brian O'Conner, closeFriend, Roman Pearce]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman Pearce
Context triple: [Brian O'Conner, closeFriend, Roman Pearce]
  • A. Roman Pearce chosen
    Roman Pearce is a fast-talking, comedic street racer and member of Dominic Toretto's crew in the Fast & Furious film franchise.
  • B. Mark Pearce
    Mark Pearce is known primarily as the husband of acclaimed British novelist and short story writer Angela Carter.
  • C. Anthony Tiffith
    Anthony Tiffith is an American music executive and entrepreneur best known as the founder and CEO of the influential hip-hop label Top Dawg Entertainment, home to artists like Kendrick Lamar and SZA.
  • D. Frank Pearce
    Frank Pearce is a video game developer and co-founder of Blizzard Entertainment, known for helping build some of the most influential franchises in modern gaming.
  • E. Alexander Parris
    Alexander Parris was a prominent 19th-century American architect and engineer best known for his austere Greek Revival and early granite public buildings in New England.
  • 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_69d6aacca1048190b39dbbc2174616fa completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7fc30f5d48190bb273df4c9e583a9 completed April 9, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b8025744819091312adddeb75347 completed April 20, 2026, 5:22 a.m.
Created at: April 8, 2026, 9:33 p.m.