Triple

T15169639
Position Surface form Disambiguated ID Type / Status
Subject Tin Men E362449 entity
Predicate cinematographyBy P1953 FINISHED
Object Peter Sova E259291 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: Peter Sova | Statement: [Tin Men, cinematographyBy, Peter Sova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Sova
Context triple: [Tin Men, cinematographyBy, Peter Sova]
  • A. Peter Sova chosen
    Peter Sova was a Czech-American cinematographer known for his stylish visual work on films such as "Lucky Number Slevin" and collaborations with directors like Barry Levinson.
  • B. Martin Kove
    Martin Kove is an American actor best known for his role as the ruthless sensei John Kreese in the Karate Kid film series and its sequel series Cobra Kai.
  • C. John Blutarsky
    John Blutarsky is a boisterous, hard-partying fraternity member and iconic comedic character from the film "National Lampoon's Animal House," famously portrayed by John Belushi.
  • D. Michael Socha
    Michael Socha is an English actor known for his roles in television dramas and fantasy series, including prominent parts in shows like "Being Human" and "Once Upon a Time in Wonderland."
  • E. Peter Gvozdas
    Peter Gvozdas is a film editor known for his work on the movie "The Babysitter."
  • 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_69d85a087b7c81908baa94a53dac8d68 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0064dba588190a4341775b472a6d3 completed April 15, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd27f2f481909dc26889c973932e completed May 9, 2026, 7:07 a.m.
Created at: April 10, 2026, 3:08 a.m.