Triple

T20700729
Position Surface form Disambiguated ID Type / Status
Subject Somebody Loves Me E508772 entity
Predicate hasCastMember P2308 FINISHED
Object Robert Keith 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: Robert Keith | Statement: [Somebody Loves Me, hasCastMember, Robert Keith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Keith
Context triple: [Somebody Loves Me, hasCastMember, Robert Keith]
  • A. Robert Keith chosen
    Robert Keith was an American character actor known for his prolific work in film and television from the 1920s through the 1960s, often portraying authoritative or paternal figures.
  • B. Gene Kirkwood
    Gene Kirkwood is an American film producer known for his work on notable movies such as "Rocky" and other popular Hollywood projects.
  • C. James Keith
    James Keith was a Scottish soldier and Jacobite general who later became a celebrated field marshal in the Prussian Army under Frederick the Great.
  • D. Kenneth Keith
    Kenneth Keith was the husband of American socialite and fashion icon Slim Hawks (later Slim Keith), known primarily in relation to her prominent presence in mid-20th-century high society.
  • E. Brian McKinley
    Brian McKinley is a member of the RTX team, a group known for its involvement in gaming and online content creation.
  • 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_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c18bfac08190bf80beeb3ce1951a completed April 21, 2026, 12:15 a.m.
Created at: April 16, 2026, 12:12 p.m.