Triple

T17584203
Position Surface form Disambiguated ID Type / Status
Subject John Harrington E428277 entity
Predicate familyName P18 FINISHED
Object Harrington 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: Harrington | Statement: [John Harrington, familyName, Harrington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harrington
Context triple: [John Harrington, familyName, Harrington]
  • A. Harrington chosen
    Harrington is a surname of English and Irish origin borne by numerous notable individuals across fields such as politics, science, and the arts.
  • B. Harrington
    Harrington is a small coastal town in New South Wales, Australia, known for its beaches, fishing, and proximity to the Manning River and Crowdy Bay National Park.
  • C. Hannan
    Hannan is a coastal city in southern Osaka Prefecture, Japan, known for its fishing industry and proximity to Osaka Bay.
  • D. Hannington
    Hannington is a small rural village in Wiltshire, England, known for its traditional English countryside setting and historic character.
  • E. Herron
    Herron is the maiden surname of Helen Herron Taft, the First Lady of the United States from 1909 to 1913 and wife of President William Howard Taft.
  • 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_69d889e1030481909950e140c63255b9 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e463d015fc8190b2dd897026d6fcb5 completed April 19, 2026, 5:10 a.m.
Created at: April 10, 2026, 5:50 a.m.