Triple

T20403118
Position Surface form Disambiguated ID Type / Status
Subject Maud Adams E500387 entity
Predicate familyName P18 FINISHED
Object Wikström 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: Wikström | Statement: [Maud Adams, familyName, Wikström]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wikström
Context triple: [Maud Adams, familyName, Wikström]
  • A. Wikström chosen
    Wikström is the Swedish family name of Maud Adams, the actress best known for her roles in James Bond films.
  • B. Wikstrom
    Wikstrom is a Steel-type specialist and one of the Elite Four members that players battle in the Kalos region of the Pokémon series.
  • C. Bäckström
    Bäckström is a Swedish surname most prominently associated with NHL ice hockey star Nicklas Bäckström.
  • D. Grafström
    Grafström is a Swedish surname most notably associated with Gillis Grafström, a three-time Olympic gold medalist in figure skating.
  • E. Wigström
    Wigström is a Swedish surname most notably associated with Henrik Wigström, a renowned Fabergé workmaster of the late 19th and early 20th centuries.
  • 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6799080cc819096dc31f41d1d7b49 completed April 20, 2026, 7:08 p.m.
Created at: April 16, 2026, 11:29 a.m.