Triple

T8620818
Position Surface form Disambiguated ID Type / Status
Subject Peter Andrews E204157 entity
Predicate partOfProfessionalPracticeOf P84475 FINISHED
Object Steven Soderbergh E199780 NE FINISHED

How this triple was built (3 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: Steven Soderbergh | Statement: [Peter Andrews, partOfProfessionalPracticeOf, Steven Soderbergh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven Soderbergh
Context triple: [Peter Andrews, partOfProfessionalPracticeOf, Steven Soderbergh]
  • A. Steven Soderbergh chosen
    Steven Soderbergh is an Academy Award–winning American filmmaker known for his innovative, genre-spanning work in films such as "Sex, Lies, and Videotape," the "Ocean's" trilogy, and "Traffic."
  • B. Stephen Gaghan
    Stephen Gaghan is an American screenwriter and director best known for his politically charged, multi-narrative films such as "Traffic" and "Syriana."
  • C. David Fincher
    David Fincher is an acclaimed American film director and producer known for his dark, stylish thrillers such as Se7en, Fight Club, and The Social Network.
  • D. Paul Thomas Anderson
    Paul Thomas Anderson is an acclaimed American filmmaker known for his character-driven, stylistically distinctive films such as "Boogie Nights," "Magnolia," and "There Will Be Blood."
  • E. Gus Van Sant
    Gus Van Sant is an American filmmaker known for his distinctive independent cinema style and acclaimed films such as "Good Will Hunting," "Milk," and "My Own Private Idaho."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: partOfProfessionalPracticeOf
Context triple: [Peter Andrews, partOfProfessionalPracticeOf, Steven Soderbergh]
  • A. regionOfPractice
    Indicates the geographic area or jurisdiction in which an entity regularly conducts its professional activities or services.
  • B. regulatesProfessionalPracticeIn
    Indicates that one entity has the authority or role to control, oversee, or set rules for how a professional activity is conducted within a particular domain or jurisdiction.
  • C. professionServed
    Indicates that an entity has performed work or provided services in a particular profession or occupational role.
  • D. practicedMedicineIn
    Indicates that a person engaged in the professional practice of medicine within a specified location or jurisdiction.
  • E. hasLanguageOfPractice
    Indicates that an entity uses or operates in a particular language as its regular or primary medium of practice.
  • F. None of above. chosen

Provenance (5 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_69ca832ceab8819096e4a9f546695079 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc5730309081909a9a0256c9bf5f8f completed March 31, 2026, 11:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cfa00aa93c819094884d5bbaa5a264 completed April 3, 2026, 11:10 a.m.
PD Predicate disambiguation batch_69cc455906f8819082edd79cb4a1cf28 completed March 31, 2026, 10:06 p.m.
PDg Predicate description generation batch_69cc572d99bc819097f36b140c2ee1ce completed March 31, 2026, 11:22 p.m.
Created at: March 30, 2026, 6:26 p.m.