Triple

T20840969
Position Surface form Disambiguated ID Type / Status
Subject West Penwith E513100 entity
Predicate contains P35 FINISHED
Object Mousehole 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: Mousehole | Statement: [West Penwith, contains, Mousehole]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mousehole
Context triple: [West Penwith, contains, Mousehole]
  • A. Mousehole chosen
    Mousehole is a small, picturesque fishing village and harbour on the coast of Cornwall in southwest England, known for its narrow streets, traditional cottages, and scenic seaside views.
  • B. Galtymore
    Galtymore is a prominent mountain in the Galtee range on the border of Counties Limerick and Tipperary in Ireland, known for its challenging hikes and scenic views.
  • C. Mousehole Harbour
    Mousehole Harbour is a picturesque traditional fishing harbour and tourist spot in the village of Mousehole on the south coast of Cornwall, England.
  • D. Carnon
    Carnon is a seaside resort town in southern France, known for its marina and Mediterranean beaches near Montpellier.
  • E. Lostwithiel
    Lostwithiel is a historic town and former parliamentary borough in Cornwall, England, known for its medieval architecture and past political significance.
  • 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_69e0b4cf62a88190bbf92351e9e57259 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c34b17b88190b3290bd5100ad2ad completed April 21, 2026, 12:22 a.m.
Created at: April 16, 2026, 12:43 p.m.