Triple

T22428273
Position Surface form Disambiguated ID Type / Status
Subject Holmes & Watson E554428 entity
Predicate starring P1507 FINISHED
Object Kelly Macdonald 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: Kelly Macdonald | Statement: [Holmes & Watson, starring, Kelly Macdonald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelly Macdonald
Context triple: [Holmes & Watson, starring, Kelly Macdonald]
  • A. Kelly Macdonald chosen
    Kelly Macdonald is a Scottish actress known for her roles in films like "Trainspotting" and "No Country for Old Men" and in television series such as "Boardwalk Empire."
  • B. Jennifer Dempsie
    Jennifer Dempsie is a Scottish political figure and campaign strategist known for her involvement with the Scottish National Party and work on independence-related campaigns.
  • C. Suzanne Mackie
    Suzanne Mackie is a British television and film producer known for her work on acclaimed projects such as "The Crown" and other high-profile UK dramas.
  • D. Kelly Reilly
    Kelly Reilly is an English actress known for her roles in films like "Flight" and the "Sherlock Holmes" series, as well as the television drama "Yellowstone."
  • E. Alison Pill
    Alison Pill is a Canadian actress known for her versatile performances in film, television, and theater, including prominent roles in projects like "Scott Pilgrim vs. the World," "The Newsroom," and "Star Trek: Picard."
  • 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_69e11e4f2d0c819091aa3558ea2ee630 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15a2f054c819093fbe173c8a4a544 completed April 29, 2026, 1:09 a.m.
Created at: April 16, 2026, 8:47 p.m.