Triple

T26154293
Position Surface form Disambiguated ID Type / Status
Subject Bermondsey and Old Southwark (UK Parliament constituency) E659913 entity
Predicate representedByFrom P177097 FINISHED
Object Neil Coyle from 2015 LITERAL 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: Neil Coyle from 2015 | Statement: [Bermondsey and Old Southwark (UK Parliament constituency), representedByFrom, Neil Coyle from 2015]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: representedByFrom
Context triple: [Bermondsey and Old Southwark (UK Parliament constituency), representedByFrom, Neil Coyle from 2015]
  • A. representedFrom
    Indicates that one entity serves as a representation or depiction of another entity.
  • B. representedByAttribute
    Indicates that one entity serves as an attribute-based representation or characterization of another entity.
  • C. areRepresentedBy
    Indicates that one entity serves as a representation, proxy, or stand-in for another entity.
  • D. representedByEnd
    Indicates that something is represented or characterized by its endpoint or final part.
  • E. hasRepresentationFrom
    Indicates that something serves as a representation, depiction, or encoding that originates from or is derived from another entity.
  • F. None of above. chosen

Provenance (4 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_69ee5bc5a9908190899d39ce95c6d215 completed April 26, 2026, 6:39 p.m.
NER Named-entity recognition batch_69f6f85bfba48190aba95b40642a8ca7 completed May 3, 2026, 7:25 a.m.
PD Predicate disambiguation batch_69f6f65fd1d08190b88e5e68ba268500 completed May 3, 2026, 7:16 a.m.
PDg Predicate description generation batch_69f6f854486c81909396d944a55e03ab completed May 3, 2026, 7:25 a.m.
Created at: April 26, 2026, 8:27 p.m.