Triple

T17069653
Position Surface form Disambiguated ID Type / Status
Subject Backtrack E414179 entity
Predicate director P255 FINISHED
Object Michael Petroni 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: Michael Petroni | Statement: [Backtrack, director, Michael Petroni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Petroni
Context triple: [Backtrack, director, Michael Petroni]
  • A. Michael Petroni chosen
    Michael Petroni is an Australian screenwriter and director known for his work on major fantasy and drama films and television series, including "The Chronicles of Narnia: The Voyage of the Dawn Treader."
  • B. Michael Petulla
    Michael Petulla is a musician best known as a member of the English indie folk band Noah and the Whale.
  • C. Anthony Marentino
    Anthony Marentino is a flamboyant, quick-witted wedding planner and stylist best known as Charlotte York’s close friend and eventual husband on the television series "Sex and the City."
  • D. Michael Fracasso
    Michael Fracasso is an American singer-songwriter known for his distinctive high-tenor voice and work in the Austin, Texas music scene.
  • E. Michael Fimognari
    Michael Fimognari is an American cinematographer and director known for his work on films such as "Before I Fall" and the "To All the Boys I've Loved Before" series.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbbfb1f08190807301ff6e573cf5 completed April 18, 2026, 7:30 p.m.
Created at: April 10, 2026, 5:34 a.m.