Triple

T22544359
Position Surface form Disambiguated ID Type / Status
Subject Caerphilly Mountain E557377 entity
Predicate nearbySettlement P350 FINISHED
Object Lisvane 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: Lisvane | Statement: [Caerphilly Mountain, nearbySettlement, Lisvane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisvane
Context triple: [Caerphilly Mountain, nearbySettlement, Lisvane]
  • A. Lisvane chosen
    Lisvane is an affluent suburban district and community on the northern edge of Cardiff, Wales, known for its leafy residential character and proximity to countryside.
  • B. Milldown
    Milldown is a notable summit in the Rhinns of Kells range in the Galloway Hills of southwest Scotland, popular with hillwalkers for its rounded grassy slopes and expansive views.
  • C. Hazeldean
    Hazeldean is a rural locality and small town situated within Queensland’s Somerset Region in Australia.
  • D. Southbourne
    Southbourne is a village and civil parish in West Sussex, England, situated near Chichester on the south coast.
  • E. Southbourne
    Southbourne is a coastal suburb in the Bournemouth area of Dorset, England, known for its sandy beaches and residential character.
  • 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_69e11e58662081909ae346ab384514ca completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f34a0688190ad55be067db8e21b completed April 29, 2026, 1:30 a.m.
Created at: April 16, 2026, 8:51 p.m.