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.