Triple

T14528905
Position Surface form Disambiguated ID Type / Status
Subject Paul Dresser E340851 entity
Predicate familyName P18 FINISHED
Object Dresser E846542 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: Dresser | Statement: [Paul Dresser, familyName, Dresser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dresser
Context triple: [Paul Dresser, familyName, Dresser]
  • A. Dresser chosen
    Dresser is a surname of English origin borne by various notable individuals, including American socialite Edith Stuyvesant Dresser.
  • B. Solberg Cabinet
    The Solberg Cabinet was the Norwegian government led by Prime Minister Erna Solberg from 2013 to 2021, characterized by a center-right coalition that included the Christian Democratic Party.
  • C. Stickley
    Stickley is a surname most prominently associated with Gustav Stickley, an influential American furniture maker and leading figure in the Arts and Crafts movement.
  • D. Andersson Cabinet
    The Andersson Cabinet was the Swedish government led by Social Democratic Prime Minister Magdalena Andersson, notable as Sweden’s first female-led cabinet.
  • E. Pierson cabinet
    The Pierson cabinet was a Dutch liberal government led by Prime Minister Nicolaas Pierson that governed the Netherlands around the turn of the 20th century.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dea051bc608190ad4d516c5e7bca43 completed April 14, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a547c408190a1a19e12aac1d5bd completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:22 a.m.