Triple

T6449151
Position Surface form Disambiguated ID Type / Status
Subject Pillow Talk E139818 entity
Predicate musicBy P1952 FINISHED
Object Frank De Vol E211462 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: Frank De Vol | Statement: [Pillow Talk, musicBy, Frank De Vol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank De Vol
Context triple: [Pillow Talk, musicBy, Frank De Vol]
  • A. Frank De Vol chosen
    Frank De Vol was an American arranger, composer, and conductor best known for his film and television scores and theme music during the mid-20th century.
  • B. Don Otten
    Don Otten was an American professional basketball center who played in the early years of the NBA, including for the Tri-Cities Blackhawks.
  • C. Hans Bonte
    Hans Bonte is a Belgian politician known for serving as the mayor of Vilvoorde and as a member of the federal parliament.
  • D. Volkert van der Graaf
    Volkert van der Graaf is a Dutch environmental and animal-rights activist best known as the assassin of politician Pim Fortuyn in 2002.
  • E. John Du Prez
    John Du Prez is a British composer and musician best known for his film scores and long-running collaboration with the comedy group Monty Python.
  • 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_69c008b301948190a35854e5284dc822 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c069b1a61c81908610264c098d25b0 completed March 22, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64bd290c481909f543cc03eee98bf completed March 27, 2026, 9:20 a.m.
Created at: March 22, 2026, 4:47 p.m.