Triple

T17399564
Position Surface form Disambiguated ID Type / Status
Subject One Crazy Summer E423050 entity
Predicate starring P1507 FINISHED
Object John Matuszak 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: John Matuszak | Statement: [One Crazy Summer, starring, John Matuszak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Matuszak
Context triple: [One Crazy Summer, starring, John Matuszak]
  • A. John Matuszak chosen
    John Matuszak was an American football defensive end turned actor, best known for playing Sloth in the film "The Goonies."
  • B. Michael Sarnoski
    Michael Sarnoski is an American filmmaker and screenwriter best known for directing the acclaimed drama "Pig" and later helming the horror prequel "A Quiet Place: Day One."
  • C. William Poduska
    William Poduska is an American entrepreneur and computer engineer best known for founding multiple influential high-technology companies, including Apollo Computer.
  • D. Philip Hulitar
    Philip Hulitar was an American fashion designer and philanthropist known for his elegant couture work and for supporting the arts, including through the sculpture garden that bears his name.
  • E. Ron Smerczak
    Ron Smerczak was a South African actor known for his character roles in film and television, including appearances in international action and adventure movies.
  • 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_69d889d710288190bf0f4762801fefae completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43ac0596481908c400916d5c1b971 completed April 19, 2026, 2:15 a.m.
Created at: April 10, 2026, 5:45 a.m.