Triple

T14997375
Position Surface form Disambiguated ID Type / Status
Subject Saga Domain E373992 entity
Predicate capital P234 FINISHED
Object Saga Castle E323064 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: Saga Castle | Statement: [Saga Domain, capital, Saga Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saga Castle
Context triple: [Saga Domain, capital, Saga Castle]
  • A. Saga Castle chosen
    Saga Castle is a historic Japanese castle in Saga Prefecture, known for its reconstructed wooden palace and role as a former seat of regional feudal power.
  • B. Leap Castle
    Leap Castle is a historic Irish fortress in County Offaly, reputed to be one of the most haunted castles in the world.
  • C. Drakensteyn Castle
    Drakensteyn Castle is a 17th-century moated country house in the Netherlands best known as the private residence of former Queen Beatrix.
  • D. Red Castle
    Red Castle is a ruined medieval fortress overlooking Lunan Bay on the east coast of Scotland.
  • E. King’s Castle
    King’s Castle is a historic coastal fortification in Bermuda that forms part of the UNESCO-listed defenses of the Town of St. George.
  • 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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded718e4288190b5e144f82299a194 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe969c3ba88190899f06b185e94ccf completed May 9, 2026, 2:06 a.m.
Created at: April 10, 2026, 2:54 a.m.