Triple
T28108116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Voice of China |
E710415
|
entity |
| Predicate | contentRegulation |
P110926
|
FINISHED |
| Object | subject to Chinese government censorship |
—
|
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: subject to Chinese government censorship | Statement: [Voice of China, contentRegulation, subject to Chinese government censorship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contentRegulation Context triple: [Voice of China, contentRegulation, subject to Chinese government censorship]
-
A.
regulatesContentFor
Indicates that one entity controls, manages, or sets rules governing the content produced, shared, or accessed by another entity.
-
B.
regulatesContentBy
chosen
Indicates that one entity controls, directs, or sets rules for the nature, form, or distribution of another entity’s content.
-
C.
contentRestriction
Indicates that access to or use of certain content is limited or controlled based on specified rules or conditions.
-
D.
regulationAtIssue
Indicates that a specific regulation is the subject of concern, dispute, or analysis in the given context.
-
E.
displayRegulation
Indicates that an entity presents or shows a regulation or set of rules, making it visible or accessible to others.
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1c555081908787dbf76147f180 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 27, 2026, 9:09 p.m.