Triple

T30716265
Position Surface form Disambiguated ID Type / Status
Subject 中共中央 E782029 entity
Predicate 权威来源 P83832 FINISHED
Object 中国共产党章程 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: 中国共产党章程 | Statement: [中共中央, 权威来源, 中国共产党章程]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 权威来源
Context triple: [中共中央, 权威来源, 中国共产党章程]
  • A. isOfficialSourceFor chosen
    Indicates that one entity is recognized as an authoritative or formally sanctioned provider of information or content about another entity.
  • B. authorityNamedOn
    Indicates that a specific authority or authoritative entity is explicitly identified by name in relation to another entity or record.
  • C. relevantAuthority
    Indicates that an entity has official power, jurisdiction, or responsibility over another entity or matter within a given context.
  • D. hasSourceOfData
    Indicates that one entity serves as the origin or provider of the data used or referenced by another entity.
  • E. claimedAuthorityFrom
    Indicates that one entity asserts its authority, legitimacy, or right to act is derived from another specified source or 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_69f224acd24481908ed5f96f0d69b5dd completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f68c5343b8819082ded39e2e8ee1c8 completed May 2, 2026, 11:44 p.m.
PD Predicate disambiguation batch_69f6861170d08190bb98be609d436f84 completed May 2, 2026, 11:17 p.m.
Created at: April 29, 2026, 8:35 p.m.