Triple

T8034264
Position Surface form Disambiguated ID Type / Status
Subject A484 road E187063 entity
Predicate region P40 FINISHED
Object Ceredigion E43732 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: Ceredigion | Statement: [A484 road, region, Ceredigion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ceredigion
Context triple: [A484 road, region, Ceredigion]
  • A. Ceredigion chosen
    Ceredigion is a coastal county in west Wales known for its rugged Cardigan Bay shoreline, rural landscapes, and Welsh-speaking communities.
  • B. Pembrokeshire
    Pembrokeshire is a coastal county in southwest Wales renowned for its rugged cliffs, sandy beaches, and the Pembrokeshire Coast National Park.
  • C. Carmarthenshire
    Carmarthenshire is a largely rural county in southwest Wales known for its market towns, rich agricultural land, and scenic landscapes stretching from the Tywi Valley to the Carmarthen Bay coast.
  • D. Powys
    Powys is a large, predominantly rural county in mid-Wales known for its mountainous landscapes, market towns, and extensive agricultural areas.
  • E. Gwynedd
    Gwynedd is a county and preserved lieutenancy area in north-west Wales known for its rugged coastline, mountains including much of Snowdonia, and strong Welsh language and cultural heritage.
  • 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_69ca82ae2d1081909dbfee42b41db419 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3ef50f4c8190a895ac301f182734 completed March 31, 2026, 3:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69cea7d3587881909539a7bea05e328a completed April 2, 2026, 5:30 p.m.
Created at: March 30, 2026, 5:22 p.m.