Triple

T20861015
Position Surface form Disambiguated ID Type / Status
Subject Par railway station E513616 entity
Predicate servesArea P82 FINISHED
Object Fowey 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: Fowey | Statement: [Par railway station, servesArea, Fowey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fowey
Context triple: [Par railway station, servesArea, Fowey]
  • A. Fowey chosen
    Fowey is a historic port and popular tourist town on the south coast of Cornwall in southwest England, known for its picturesque harbour and maritime heritage.
  • B. Gore Bay
    Gore Bay is a small town and harbor community located on the north shore of Manitoulin Island in Ontario, Canada.
  • C. Knollsea
    Knollsea is a fictional coastal town in Thomas Hardy’s Wessex, modeled on the real seaside resort of Swanage in Dorset, England.
  • D. Wyre Sound
    Wyre Sound is a narrow strait in the Orkney Islands of Scotland, separating the islands of Rousay and Wyre and known for its strong tidal currents.
  • E. Feall Bay
    Feall Bay is a scenic sandy beach on the Isle of Coll in Scotland, known for its unspoiled dunes, clear waters, and abundant wildlife.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3aba3d0819093431f38f0095a71 completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:44 p.m.