Triple

T25399966
Position Surface form Disambiguated ID Type / Status
Subject 大阪城 E636391 entity
Predicate 再建の歴史 P111643 FINISHED
Object 江戸時代に徳川幕府が再建 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: 江戸時代に徳川幕府が再建 | Statement: [大阪城, 再建の歴史, 江戸時代に徳川幕府が再建]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 再建の歴史
Context triple: [大阪城, 再建の歴史, 江戸時代に徳川幕府が再建]
  • A. historicalReconstruction
    Indicates the process of recreating or inferring past events, conditions, or states of affairs based on available evidence or records.
  • B. rebuiltInDynasty chosen
    Indicates that something was reconstructed or significantly renovated during a specified dynasty.
  • C. rebuiltAsPalace
    Indicates that a structure or building was reconstructed or transformed into a palace.
  • D. سبب الأهمية التاريخية
    Indicates that something serves as the reason or basis for another thing’s historical significance.
  • E. historicalEraRecreated
    Indicates that a past historical era has been reconstructed or simulated, typically for representation, study, or experiential purposes.
  • 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.