Triple

T15616778
Position Surface form Disambiguated ID Type / Status
Subject Graham Rogers E375433 entity
Predicate hasActedIn P15620 FINISHED
Object Bull E548603 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: Bull | Statement: [Graham Rogers, hasActedIn, Bull]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bull
Context triple: [Graham Rogers, hasActedIn, Bull]
  • A. Bull
    Bull was the notorious nickname of Eugene "Bull" Connor, the Birmingham, Alabama public safety commissioner whose brutal enforcement of racial segregation during the Civil Rights Movement made him a national symbol of racist oppression.
  • B. Bull chosen
    Bull is an American legal drama television series that follows a brilliant trial consultant and his team as they analyze juries and craft courtroom strategies.
  • C. Bull
    Bull is a common English surname borne by various notable individuals across fields such as politics, sports, and the arts.
  • D. Bull
    Bull is the common nickname of U.S. Navy Admiral William F. "Bull" Halsey Jr., a prominent World War II naval commander in the Pacific Theater.
  • E. One Bull
    One Bull was a prominent Hunkpapa Lakota warrior and relative of Sitting Bull who fought in key conflicts during the late 19th-century Plains Wars.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e980b748190b43c0b650bf1e629 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff56dd1e4c819090bf3cd4425b39b7 completed May 9, 2026, 3:46 p.m.
Created at: April 10, 2026, 4:13 a.m.