Triple

T4964799
Position Surface form Disambiguated ID Type / Status
Subject Swansea Castle E111495 entity
Predicate locatedInHistoricRegion P5057 FINISHED
Object Gower Lordship E402009 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: Gower Lordship | Statement: [Swansea Castle, locatedInHistoricRegion, Gower Lordship]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gower Lordship
Context triple: [Swansea Castle, locatedInHistoricRegion, Gower Lordship]
  • A. Gower chosen
    Gower is a UK parliamentary constituency in South Wales, named after the Gower Peninsula and represented in the House of Commons.
  • B. Highworth
    Highworth is a historic market town in Wiltshire, England, known for its elevated position and traditional architecture.
  • C. Wormleighton
    Wormleighton is an English village and historic estate in Warwickshire that served as an ancestral seat of the aristocratic Spencer family.
  • D. Manor Valley
    Manor Valley is a scenic valley in the Scottish Borders known as a gateway for walking and outdoor activities in the surrounding hills.
  • E. Gamlingay
    Gamlingay is a rural village and civil parish in Cambridgeshire, England, known for its historic architecture and surrounding countryside.
  • 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_69bd4419393c819086319a6fe4bf8542 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd71f693b48190b3523cd314303cbe completed March 20, 2026, 4:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69be81edb99481909397559479c3badb completed March 21, 2026, 11:33 a.m.
Created at: March 20, 2026, 1:32 p.m.