Triple

T8401494
Position Surface form Disambiguated ID Type / Status
Subject Kidwelly E198381 entity
Predicate nearbyVillage P4647 FINISHED
Object Ferryside E518549 NE 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: Ferryside | Statement: [Kidwelly, nearbyVillage, Ferryside]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ferryside
Context triple: [Kidwelly, nearbyVillage, Ferryside]
  • A. Ferryside chosen
    Ferryside is a small coastal village in Carmarthenshire, Wales, situated on the estuary of the River Towy and known for its scenic views and maritime heritage.
  • B. Harbourside
    Harbourside is Bristol’s regenerated waterfront district, known for its cultural attractions, restaurants, and scenic views along the city’s historic docks.
  • C. The Quays
    The Quays is a redeveloped waterfront area in Salford, Greater Manchester, known for its modern architecture, cultural attractions, and leisure facilities along the Manchester Ship Canal.
  • D. Fairwater
    Fairwater is a residential neighbourhood within the town of Cwmbran in South Wales.
  • E. The Harbour
    The Harbour is a creative work by Croatian illustrator, animator, and filmmaker Milan Trenc, known for his distinctive, surreal visual style.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca8310df9c8190b25f16161cca3e41 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cb824da3148190bfa3a1abfdfa02de completed March 31, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde8789a608190a3503f544a19d204 completed April 2, 2026, 3:54 a.m.
Created at: March 30, 2026, 6:04 p.m.