Triple

T13779708
Position Surface form Disambiguated ID Type / Status
Subject Sharknado E331101 entity
Predicate producer P490 FINISHED
Object David Michael Latt E460631 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 Latt | Statement: [Sharknado, producer, David Michael Latt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Michael Latt
Context triple: [Sharknado, producer, David Michael Latt]
  • A. David Michael Latt chosen
    David Michael Latt is an American film producer, director, and co-founder of the low-budget production company The Asylum, known for mockbusters and genre films.
  • B. Brian Latture
    Brian Latture is a music producer known for his work on LL Cool J’s 1989 hip hop album "Walking with a Panther."
  • C. Matt Lattanzi
    Matt Lattanzi is an American actor and former dancer best known for his roles in 1980s films and for his marriage to singer and actress Olivia Newton-John.
  • D. Stephen Michael Largent
    Stephen Michael Largent is a former American football wide receiver and Hall of Famer who became a U.S. Congressman from Oklahoma.
  • E. Greg Latta
    Greg Latta was an American professional football tight end who played in the World Football League and the NFL, most notably for the Chicago Bears.
  • 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_69d81c583b0081909e408a17db517a21 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02460a688190a27874f8d35819c7 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b07670b08190a205d3c7ccb9dded completed May 3, 2026, 8:30 p.m.
Created at: April 9, 2026, 10:11 p.m.