Triple

T20223567
Position Surface form Disambiguated ID Type / Status
Subject Dan Stevens E495318 entity
Predicate workedWith P398 FINISHED
Object Michelle Dockery 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: Michelle Dockery | Statement: [Dan Stevens, workedWith, Michelle Dockery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michelle Dockery
Context triple: [Dan Stevens, workedWith, Michelle Dockery]
  • A. Michelle Dockery chosen
    Michelle Dockery is an English actress best known for her role as Lady Mary Crawley in the television series "Downton Abbey."
  • B. Anne-Marie Duff
    Anne-Marie Duff is an acclaimed English actress known for her powerful performances in television dramas such as "Shameless" and "The Virgin Queen," as well as in film and theatre.
  • C. Jessica Riley
    Jessica Riley is a flirtatious and popular teenager who is one of the playable protagonists in the horror video game Until Dawn.
  • D. Miranda Richardson
    Miranda Richardson is an acclaimed English actress known for her versatile performances in film, television, and theatre, including notable roles in "The Crying Game," "Damage," and the "Harry Potter" series.
  • E. Caroline Quentin
    Caroline Quentin is an English actress and television presenter best known for her comedic and dramatic roles in popular British series such as "Men Behaving Badly" and "Jonathan Creek."
  • 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.