Triple

T15103870
Position Surface form Disambiguated ID Type / Status
Subject Police Academy 3: Back in Training E360736 entity
Predicate stars P1956 FINISHED
Object Art Metrano E1001299 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: Art Metrano | Statement: [Police Academy 3: Back in Training, stars, Art Metrano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Art Metrano
Context triple: [Police Academy 3: Back in Training, stars, Art Metrano]
  • A. Art Metrano chosen
    Art Metrano was an American actor and comedian best known for his role as the bumbling police captain Ernie Mauser in the "Police Academy" film series.
  • B. Ed Calle
    Ed Calle is a Venezuelan-born saxophonist, composer, and educator known for his work in Latin jazz and as a prolific session musician.
  • C. Santo Loquasto
    Santo Loquasto is an acclaimed American production, set, and costume designer best known for his extensive work on Broadway and in films, including frequent collaborations with director Woody Allen.
  • D. Frank Cardea
    Frank Cardea is an American television writer and producer best known for his long-running work on the crime drama series "NCIS."
  • E. Michael Cerda
    Michael Cerda is a media and technology executive and producer known for his work in digital entertainment and content development.
  • 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_69d85a0491ec8190830960be8fafb994 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00551521c8190b48d1a074bb4bdfc completed April 15, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae274f6881908931569efc09996e completed May 9, 2026, 3:46 a.m.
Created at: April 10, 2026, 3:05 a.m.