Triple

T8187934
Position Surface form Disambiguated ID Type / Status
Subject Blaina E191232 entity
Predicate hasRiver P165 FINISHED
Object River Ebbw Fach E474427 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: River Ebbw Fach | Statement: [Blaina, hasRiver, River Ebbw Fach]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Ebbw Fach
Context triple: [Blaina, hasRiver, River Ebbw Fach]
  • A. River Ebbw chosen
    River Ebbw is a river in south-east Wales that flows through former industrial valleys of Gwent before joining the River Usk near Newport.
  • B. River Dwyryd
    River Dwyryd is a river in Gwynedd, Wales, that flows through Snowdonia to reach the estuary near Porthmadog on the west coast.
  • C. River Taff
    The River Taff is a major river in South Wales that flows through Merthyr Tydfil and Cardiff before reaching the Bristol Channel.
  • D. River Honddu
    River Honddu is a small river in Powys, Wales, known for flowing through the Brecon Beacons area before joining the River Monnow.
  • E. Neath
    Neath is a historic industrial and market town in South Wales, known for its Roman and medieval heritage and its role in the coal and steel industries.
  • 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_69ca82c5b6948190a583c096fb0a6c71 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4d9f4a488190b39bdc1792646914 completed March 31, 2026, 4:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce6cacb9188190853bc649c3c75d97 completed April 2, 2026, 1:18 p.m.
Created at: March 30, 2026, 5:41 p.m.