Triple

T10566581
Position Surface form Disambiguated ID Type / Status
Subject Alan Bullock E249364 entity
Predicate familyName P18 FINISHED
Object Bullock E738827 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: Bullock | Statement: [Alan Bullock, familyName, Bullock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bullock
Context triple: [Alan Bullock, familyName, Bullock]
  • A. Bullock
    Bullock is a fictional CIA official, often portrayed as a volatile and over-the-top supervisor character in animated television comedy.
  • B. Bullock chosen
    Bullock is the surname of acclaimed American actress and producer Sandra Bullock, known for her versatile roles in film and television.
  • C. Bullock's
    Bullock's was a prominent American department store chain based in Southern California, known for its upscale merchandise and influential role in West Coast retail during the 20th century.
  • D. Mule Suttles
    Mule Suttles was a legendary power-hitting first baseman and outfielder in Negro league baseball, renowned for his prodigious home runs and status as one of the era’s greatest sluggers.
  • E. Bull Montana
    Bull Montana was an Italian-born American character actor and former professional wrestler known for his villainous and comedic roles in silent and early sound films.
  • 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_69d381c8bd708190acf3d275c908251e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d5272ce78c8190bf3227053ef88a48 completed April 7, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69d94b42879481909f9c98b2579c10a1 completed April 10, 2026, 7:10 p.m.
Created at: April 6, 2026, 12:36 p.m.