Triple

T20700721
Position Surface form Disambiguated ID Type / Status
Subject Somebody Loves Me E508772 entity
Predicate musicBy P1952 FINISHED
Object Van Cleave 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: Van Cleave | Statement: [Somebody Loves Me, musicBy, Van Cleave]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Van Cleave
Context triple: [Somebody Loves Me, musicBy, Van Cleave]
  • A. Van Cleave chosen
    Van Cleave was an American composer and orchestrator best known for his innovative film and television scores, particularly in the science fiction genre.
  • B. Van Clève
    Van Clève is a French family name most notably borne by the sculptor Corneille Van Clève, active in the late 17th and early 18th centuries.
  • C. Elam Lynds
    Elam Lynds was a 19th-century American prison warden and reformer known for implementing strict disciplinary systems in early U.S. penitentiaries.
  • D. Hut Stricklin
    Hut Stricklin is an American former NASCAR driver best known for his long Cup Series career and his association with the famed Alabama Gang racing group.
  • E. Stone Cates
    Stone Cates is a beloved fictional character from the soap opera "General Hospital," best known for his tragic HIV/AIDS storyline and deep emotional impact on the show's characters and viewers.
  • 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.