Triple

T25399931
Position Surface form Disambiguated ID Type / Status
Subject 大阪城 E636391 entity
Predicate 天守の特徴 P57218 FINISHED
Object 五層八階構造 LITERAL 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: 五層八階構造 | Statement: [大阪城, 天守の特徴, 五層八階構造]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 天守の特徴
Context triple: [大阪城, 天守の特徴, 五層八階構造]
  • A. towerCharacteristic chosen
    Indicates that a specified characteristic or feature is attributed to a tower.
  • B. towerShape
    Indicates that one entity has the physical form or outline of a tower in relation to another entity.
  • C. battlementFeature
    Indicates that one architectural element functions as a defensive battlement or is a structural feature of a battlement.
  • D. hasDomeOrTower
    Indicates that one entity possesses or features a dome or a tower as part of its structure.
  • E. observationTowerDesign
    Indicates a design relationship in which one entity serves as the architectural or structural design for an observation tower associated with another entity.
  • F. None of above.

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_69e75db263888190b77fff9e2827b9a2 completed April 21, 2026, 11:21 a.m.
NER Named-entity recognition batch_69f584f978a881909842e36f61b9a40a completed May 2, 2026, 5 a.m.
PD Predicate disambiguation batch_69f45d0dbc8c8190beecce679fce90a4 completed May 1, 2026, 7:58 a.m.
Created at: April 21, 2026, 1:50 p.m.