Triple

T19755274
Position Surface form Disambiguated ID Type / Status
Subject William Gibson E474484 entity
Predicate notableWork P4 FINISHED
Object Agency 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: Agency | Statement: [William Gibson, notableWork, Agency]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agency
Context triple: [William Gibson, notableWork, Agency]
  • A. Agency chosen
    An agency is an organization or business that provides specific services or acts on behalf of others, often within governmental, commercial, or creative sectors.
  • B. Benefits Agency
    The Benefits Agency was a UK government executive agency responsible for administering social security benefits to the public.
  • C. Delegate
    Delegate is a small rural town in the Snowy Monaro region of New South Wales, Australia, known for its historic buildings and proximity to the New South Wales–Victoria border.
  • D. United Agents
    United Agents is a prominent London-based talent agency representing actors, writers, directors, and other creatives across film, television, theatre, and publishing.
  • E. ACY
    ACY is the three-letter IATA airport code for Atlantic City International Airport in New Jersey, USA.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529dada081909c5b4d65247c6032 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:48 p.m.