Triple

T6719705
Position Surface form Disambiguated ID Type / Status
Subject Swords E153363 entity
Predicate hasLandmark P105 FINISHED
Object Swords Castle E170048 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: Swords Castle | Statement: [Swords, hasLandmark, Swords Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swords Castle
Context triple: [Swords, hasLandmark, Swords Castle]
  • A. Swords Castle chosen
    Swords Castle is a medieval fortified complex in Swords, County Dublin, notable as one of the best-preserved surviving castles near Dublin, Ireland.
  • B. Sandal Castle
    Sandal Castle is a ruined medieval fortress near Wakefield in West Yorkshire, England, historically significant for its role in the Wars of the Roses.
  • C. Dunyvaig Castle
    Dunyvaig Castle is a ruined medieval stronghold on the Isle of Islay in Scotland, long associated with the powerful MacDonald clan and their control of the surrounding seas.
  • D. Tous Castle
    Tous Castle is a historic medieval fortress located in Sant Martí de Tous, in Catalonia, Spain.
  • E. Ako Castle
    Ako Castle is a historic Japanese castle in Hyōgo Prefecture, best known as the stronghold associated with the legendary Forty-seven Ronin.
  • 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_69c68809b4608190a2509ddb5ab87f05 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d137084881908e04ee6b2bd45585 completed March 27, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7581d4fb081908530cfd5f7bcba24 completed March 28, 2026, 4:25 a.m.
Created at: March 27, 2026, 2:07 p.m.