Triple

T20223524
Position Surface form Disambiguated ID Type / Status
Subject Dan Stevens E495318 entity
Predicate name P16 FINISHED
Object Dan Stevens 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: Dan Stevens | Statement: [Dan Stevens, name, Dan Stevens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dan Stevens
Context triple: [Dan Stevens, name, Dan Stevens]
  • A. Dan Stevens chosen
    Dan Stevens is a British actor best known for his roles in the TV series "Downton Abbey," the live-action film "Beauty and the Beast," and various stage and screen productions.
  • B. Josh O'Connor
    Josh O'Connor is a British actor best known for his acclaimed portrayal of Prince Charles in the television series "The Crown" and roles in films such as "God's Own Country."
  • C. Matthew Reeve
    Matthew Reeve is a British-American filmmaker and activist, known for his documentary work and for continuing the legacy of his father, actor and disability advocate Christopher Reeve.
  • D. Bradley James
    Bradley James is an English actor best known for portraying Prince Arthur in the BBC fantasy series "Merlin."
  • E. Ben Barnes
    Ben Barnes is an English actor best known for his roles in films like "The Chronicles of Narnia" series and "Dorian Gray," as well as TV shows such as "Westworld" and "Shadow and Bone."
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fd827708190b798a30f4e7d533f completed April 20, 2026, 6:26 p.m.
Created at: April 11, 2026, 11:39 p.m.