Triple

T18731375
Position Surface form Disambiguated ID Type / Status
Subject Sunshine Cleaning E458041 entity
Predicate character P662 FINISHED
Object Joe Lorkowski 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: Joe Lorkowski | Statement: [Sunshine Cleaning, character, Joe Lorkowski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Lorkowski
Context triple: [Sunshine Cleaning, character, Joe Lorkowski]
  • A. Joe Lorkowski chosen
    Joe Lorkowski is a character in the film "Sunshine Cleaning," portrayed as the young son of the protagonist, Rose Lorkowski.
  • B. William Zabka
    William Zabka is an American actor best known for playing the rival bully Johnny Lawrence in the Karate Kid film series and its sequel series Cobra Kai.
  • C. Nick Wasicsko
    Nick Wasicsko was a young Yonkers, New York mayor known for his pivotal and contentious role in implementing federally mandated public housing desegregation in the late 1980s.
  • D. Alan Gwizdowski
    Alan Gwizdowski is a cinematographer known for his work on the satirical comedy film "Honk for Jesus. Save Your Soul."
  • E. John Ogrodnick
    John Ogrodnick is a former Canadian professional ice hockey left winger best known for his high-scoring NHL career, primarily with the Detroit Red Wings, during the 1980s.
  • 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d7854748190b66c4aaadfd67f29 completed April 20, 2026, 12:04 a.m.
Created at: April 10, 2026, 11:51 a.m.