Triple

T11338398
Position Surface form Disambiguated ID Type / Status
Subject Brady Corbet E268530 entity
Predicate workedWith P398 FINISHED
Object Lars von Trier E216762 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: Lars von Trier | Statement: [Brady Corbet, workedWith, Lars von Trier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lars von Trier
Context triple: [Brady Corbet, workedWith, Lars von Trier]
  • A. Lars von Trier chosen
    Lars von Trier is a provocative Danish filmmaker known for his emotionally intense, stylistically experimental films and for co-founding the Dogme 95 movement.
  • B. Thomas Vinterberg
    Thomas Vinterberg is a Danish film director and screenwriter best known as a co-founder of the Dogme 95 movement and for acclaimed films such as "Festen" and "Another Round."
  • C. Anders Refn
    Anders Refn is a Danish film editor and director known for his extensive work in Danish cinema and collaborations with prominent filmmakers, including his son Nicolas Winding Refn.
  • D. Spodsbjerg
    Spodsbjerg is a small coastal town and ferry port on the Danish island of Langeland in the Region of Southern Denmark.
  • E. Nicolas Winding Refn
    Nicolas Winding Refn is a Danish filmmaker known for his stylish, ultra-violent films such as "Drive," "Bronson," and "Only God Forgives."
  • 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_69d6aacb1f0881908c84a349fd1be047 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea008b5081908e6c6c6fc29ef936 completed April 9, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5433d3e848190ad4f51c23d5a8bb2 completed April 19, 2026, 9:03 p.m.
Created at: April 8, 2026, 9:33 p.m.