Triple

T22827186
Position Surface form Disambiguated ID Type / Status
Subject Cleddau Estuary E565691 entity
Predicate near P350 FINISHED
Object Milford Haven 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: Milford Haven | Statement: [Cleddau Estuary, near, Milford Haven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Milford Haven
Context triple: [Cleddau Estuary, near, Milford Haven]
  • A. Milford Haven chosen
    Milford Haven is a coastal town and deep-water port in Pembrokeshire, Wales, known for its large natural harbour and role in the UK energy industry.
  • B. Crosshaven
    Crosshaven is a coastal village in County Cork, Ireland, known for its large marina, sailing traditions, and scenic position at the mouth of Cork Harbour.
  • C. Newlyn
    Newlyn is a historic Cornish fishing village and harbour on the coast of southwest England, renowned for its art colony and maritime heritage.
  • D. Penryn Harbour
    Penryn Harbour is a small tidal port and waterfront area serving the historic town of Penryn in Cornwall, England.
  • E. Poldhu
    Poldhu is a coastal area in Cornwall, England, historically notable as the site of early pioneering wireless radio experiments by Guglielmo Marconi.
  • 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_69e24585ab1c81909b2b5065d15805d5 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e2832b8819091c1dfd2cd598b90 completed April 29, 2026, 3:42 a.m.
Created at: April 17, 2026, 3:34 p.m.