Triple

T14787214
Position Surface form Disambiguated ID Type / Status
Subject 太庙 E347557 entity
Predicate 相关遗产 P46818 FINISHED
Object 北京古代宫廷建筑群 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: 北京古代宫廷建筑群 | Statement: [太庙, 相关遗产, 北京古代宫廷建筑群]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 相关遗产
Context triple: [太庙, 相关遗产, 北京古代宫廷建筑群]
  • A. heritageReference
    Indicates that one entity serves as a cultural, historical, or heritage-related reference or source for another entity.
  • B. heritageFunction
    Indicates the role, use, or purpose that a heritage asset or element serves within its cultural, historical, or social context.
  • C. heritageService
    Indicates that an entity provides, manages, or is associated with services related to the preservation, interpretation, or promotion of cultural or natural heritage.
  • D. heritageComponent chosen
    Indicates that one entity forms a constituent or contributing part of another entity’s cultural or historical heritage.
  • E. heritageTransmission
    Indicates the passing down of cultural, historical, or familial heritage from one entity or generation to another.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decaa083e481908336d58d026eec32 completed April 14, 2026, 11:15 p.m.
PD Predicate disambiguation batch_69de8c090d1081909b5a9bf437499d6c completed April 14, 2026, 6:48 p.m.
Created at: April 10, 2026, 1:31 a.m.