Triple

T13702783
Position Surface form Disambiguated ID Type / Status
Subject Above the Law E328560 entity
Predicate musicBy P1952 FINISHED
Object David Michael Frank E570793 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: David Michael Frank | Statement: [Above the Law, musicBy, David Michael Frank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Michael Frank
Context triple: [Above the Law, musicBy, David Michael Frank]
  • A. David Michael Frank chosen
    David Michael Frank is an American composer best known for his work on film and television scores.
  • B. David Frank
    David Frank is a music producer best known for his work on Christina Aguilera’s hit single "Genie in a Bottle."
  • C. Brian Charles Frank
    Brian Charles Frank is a screenwriter best known for co-writing the dark comedy-drama film "Hesher."
  • D. Anthony DeLuca
    Anthony DeLuca is a character from the 1970s American sitcom "Blansky's Beauties," which followed the lives of Las Vegas showgirls and their manager.
  • E. John Filippone
    John Filippone was the husband of Maureen Reagan, the daughter of former U.S. President Ronald Reagan.
  • 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_69d8076ff62081908a7bd79889edd7a0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dcad162158819089280ee1e6b5c2cf completed April 13, 2026, 8:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69f79459192c81908132ad9813d69125 completed May 3, 2026, 6:30 p.m.
Created at: April 9, 2026, 9:54 p.m.