Triple

T13716513
Position Surface form Disambiguated ID Type / Status
Subject Innocent Lies E328913 entity
Predicate hasCastMember P2308 FINISHED
Object Stephen Dorff E161341 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: Stephen Dorff | Statement: [Innocent Lies, hasCastMember, Stephen Dorff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stephen Dorff
Context triple: [Innocent Lies, hasCastMember, Stephen Dorff]
  • A. Stephen Dorff chosen
    Stephen Dorff is an American actor known for his intense performances in films such as "Blade," "Somewhere," and numerous independent and genre movies.
  • B. Casper Van Dien
    Casper Van Dien is an American actor best known for his leading role as Johnny Rico in the science fiction film "Starship Troopers."
  • C. Steve Dorff
    Steve Dorff is an American songwriter and composer known for his prolific work in country and pop music, including numerous hits for major recording artists and film and television scores.
  • D. Luke Busey
    Luke Busey is an American actor and the son of Academy Award–nominated actor Gary Busey.
  • E. Josh Hartnett
    Josh Hartnett is an American actor known for his breakout roles in late-1990s and early-2000s films such as "The Faculty," "Pearl Harbor," and "Black Hawk Down," as well as later work in projects like the series "Penny Dreadful."
  • 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_69d80770b9bc81909f70c8c317d53cff completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dd4398f0448190810c840a82228706 completed April 13, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79d5878948190a2aaab2ba31bd1ed completed May 3, 2026, 7:09 p.m.
Created at: April 9, 2026, 9:54 p.m.