Triple

T16190043
Position Surface form Disambiguated ID Type / Status
Subject Blended E392910 entity
Predicate director P255 FINISHED
Object Frank Coraci E392925 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 Coraci | Statement: [Blended, director, Frank Coraci]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Coraci
Context triple: [Blended, director, Frank Coraci]
  • A. Frank Coraci chosen
    Frank Coraci is an American film director best known for his frequent collaborations with Adam Sandler on popular comedies such as "The Wedding Singer," "The Waterboy," and "Click."
  • B. Hank Cicalo
    Hank Cicalo is a recording engineer best known for his work on influential rock and pop albums, including projects with artists like Carole King and The Monkees.
  • C. Frank Yaconelli
    Frank Yaconelli was an Italian-American character actor and musician known for his comic supporting roles in numerous Hollywood films from the 1930s and 1940s.
  • D. Paul Falsone
    Paul Falsone is a fictional Baltimore homicide detective featured as a main character on the television series "Homicide: Life on the Street."
  • E. Joe Corallo
    Joe Corallo is a comic book writer and editor known for his work on independent and genre titles in the modern comics scene.
  • 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_69d87f1e49ac8190a311b54d32990576 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e222d4ab8081909a02e5138b29b83b completed April 17, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffff0750f08190a2fce65124d8dcc0 completed May 10, 2026, 3:44 a.m.
Created at: April 10, 2026, 5:02 a.m.