Triple

T19720206
Position Surface form Disambiguated ID Type / Status
Subject Fforestfach E473586 entity
Predicate electoralWard P16735 FINISHED
Object Cockett 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: Cockett | Statement: [Fforestfach, electoralWard, Cockett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cockett
Context triple: [Fforestfach, electoralWard, Cockett]
  • A. Cockett chosen
    Cockett is a suburban district of Swansea in South Wales, known primarily as a residential area with local amenities and transport links into the city.
  • B. Willcocks
    Willcocks is an English surname most notably associated with Sir David Willcocks, a renowned choral conductor and composer.
  • C. Coppins
    Coppins is a historic country house and former royal residence located in Iver, Buckinghamshire, England.
  • D. Cotty
    Cotty is one of the four college girls in the crime drama film "Spring Breakers," known for her involvement in the group’s hedonistic and increasingly dangerous spring break escapades.
  • E. Kock
    Kock is a town in eastern Poland known for being the site of the final major battle of the September 1939 campaign during World War II.
  • 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e64410e5548190b60e13603b6c0053 completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.