Triple

T37061590
Position Surface form Disambiguated ID Type / Status
Subject 琵琶湖 E917336 entity
Predicate 関連する文化財 P153856 FINISHED
Object 竹生島神社 NE NERFINISHED

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: 竹生島神社 | Statement: [琵琶湖, 関連する文化財, 竹生島神社]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 関連する文化財
Context triple: [琵琶湖, 関連する文化財, 竹生島神社]
  • A. culturalProperty
    Indicates that something is recognized or treated as a cultural property, typically denoting legal or heritage status tied to cultural significance.
  • B. 関連する作品
    Indicates that one work is related to another work, such as by theme, series, adaptation, or other contextual connection.
  • C. relationshipToNationalTreasures
    Indicates a specified type of connection or association that an entity has with designated national treasures.
  • D. hasCulturalHeritageLink chosen
    Indicates a relationship where one entity is culturally derived from, influenced by, or historically connected to another.
  • E. نوع_آثار_مرتبط
    Indicates a relationship where one entity is associated with another through a specific type or category of related works or artifacts.
  • 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_69f76e95fa40819091e14681087ae5e4 completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fb55de3b9c8190a7656aeab3c3ffbc completed May 6, 2026, 2:53 p.m.
PD Predicate disambiguation batch_69fb35bc92e08190bff447624e2df791 completed May 6, 2026, 12:36 p.m.
Created at: May 3, 2026, 4:14 p.m.