Triple
T26976050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hirak Raja |
E679459
|
entity |
| Predicate | censors |
P138544
|
FINISHED |
| Object | freedom of speech in Hirak |
—
|
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: freedom of speech in Hirak | Statement: [Hirak Raja, censors, freedom of speech in Hirak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: censors Context triple: [Hirak Raja, censors, freedom of speech in Hirak]
-
A.
censorshipTarget
chosen
Indicates that an entity is the object or focus of censorship by another entity or authority.
-
B.
typeOfCensorship
Indicates the specific kind or method of censorship being applied in a given context.
-
C.
coCensorWith
Indicates that two or more entities participate together in the act of censoring the same content or subject.
-
D.
wasCensored
Indicates that an entity’s content, expression, or communication was suppressed, altered, or restricted by an authority or controlling party.
-
E.
censorshipReason
Indicates the justification or cause given for why certain content is suppressed, restricted, or removed.
- 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_69eeeb507a7081909d516e1fa08b7d29 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6212856b081909baa2f2083383a48 |
completed | May 2, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:42 a.m.