Triple

T23443698
Position Surface form Disambiguated ID Type / Status
Subject Bobby Lee E565474 entity
Predicate name P16 FINISHED
Object Bobby Lee 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: Bobby Lee | Statement: [Bobby Lee, name, Bobby Lee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bobby Lee
Context triple: [Bobby Lee, name, Bobby Lee]
  • A. Bobby Lee chosen
    Bobby Lee is an American comedian and actor best known for his sketch comedy work and offbeat characters on television and in stand-up.
  • B. Buddy Lee
    Buddy Lee is the stage name of American actor and former stuntman Robert Fuller, known for his roles in classic Western television series.
  • C. Bobby Wright
    Bobby Wright is an American country music singer and guitarist known for his recordings in the 1960s and 1970s, including his version of "Room Full of Roses."
  • D. Bobby Glenn
    Bobby Glenn is an American soul singer and songwriter best known for his 1970s work that has been widely sampled in hip-hop music.
  • E. Bobby Jackson
    Bobby Jackson is a former American professional basketball guard best known for his standout college career and his role as a key sixth man in the NBA, particularly with the Sacramento Kings.
  • 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_69e24584f9488190bb32730bd2ce023e completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a64717d08190a2c25e7bbfc17a2f completed April 29, 2026, 6:33 a.m.
Created at: April 17, 2026, 5:51 p.m.