Triple

T23153024
Position Surface form Disambiguated ID Type / Status
Subject Freeheld E578368 entity
Predicate director P255 FINISHED
Object Peter Sollett 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: Peter Sollett | Statement: [Freeheld, director, Peter Sollett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Sollett
Context triple: [Freeheld, director, Peter Sollett]
  • A. Peter Sollett chosen
    Peter Sollett is an American film director and screenwriter known for character-driven independent films and offbeat romantic comedies.
  • B. Andrew Sowle
    Andrew Sowle was a 17th-century London Quaker printer and publisher known for producing early colonial American maps and religious works.
  • C. Christopher Sower
    Christopher Sower (Christoph Sauer) was an 18th-century German-American printer and publisher in Pennsylvania, known for producing one of the earliest German-language Bibles in America.
  • D. Peter Driscoll
    Peter Driscoll was a South African-born British thriller novelist best known for his politically charged suspense novels set in Africa.
  • E. Stephen Gillett
    Stephen Gillett is an American technology and business executive known for leadership roles at companies such as Starbucks, Best Buy, and Verily (Alphabet’s life sciences division).
  • 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_69e245fb8de081908f0eba7b5fd75bc4 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18efaa1fc81908fb1987dbf732f46 completed April 29, 2026, 4:54 a.m.
Created at: April 17, 2026, 4:01 p.m.