Triple

T22310867
Position Surface form Disambiguated ID Type / Status
Subject Rachel Stevenson E551507 entity
Predicate hasSurname P18 FINISHED
Object Stevenson 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: Stevenson | Statement: [Rachel Stevenson, hasSurname, Stevenson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stevenson
Context triple: [Rachel Stevenson, hasSurname, Stevenson]
  • A. Stevenson
    Stevenson is a small city in Washington State that serves as the county seat of Skamania County along the Columbia River Gorge.
  • B. Stevenson
    Stevenson is an unincorporated community in Baltimore County, Maryland, known for its suburban character and as the home of Stevenson University.
  • C. Stevenson chosen
    Stevenson is a common Scottish-origin surname borne by numerous notable figures in politics, literature, and public life.
  • D. Stevenson
    Stevenson is the given first name of American publishing executive and former presidential candidate Steve Forbes.
  • E. Thomas Stevenson
    Thomas Stevenson was a prominent 19th-century Scottish civil engineer and lighthouse designer, best known as the father of author Robert Louis Stevenson.
  • 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_69e11e46c0188190800181a4233f28fe completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1574e7fc0819080e3e85001ab2c90 completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:42 p.m.