Triple
T19105714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Дмитрий Андреевич Муратов |
E467647
|
entity |
| Predicate | публично выступал против |
P437
|
FINISHED |
| Object | цензуры в СМИ |
—
|
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: цензуры в СМИ | Statement: [Дмитрий Андреевич Муратов, публично выступал против, цензуры в СМИ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: публично выступал против Context triple: [Дмитрий Андреевич Муратов, публично выступал против, цензуры в СМИ]
-
A.
выступалаЗа
Indicates that an entity (typically a person or team) has represented or played on behalf of another entity (such as a club, organization, or country).
-
B.
emergedInOppositionTo
Indicates that one entity came into existence or gained prominence specifically as a reaction or counter-movement against another entity.
-
C.
opposedBy
chosen
Indicates that one entity actively resists, disagrees with, or works against the actions, views, or position of another entity.
-
D.
designedToOppose
Indicates that one entity is intentionally created or configured to counteract, resist, or work against another entity or process.
-
E.
secretlyOpposes
Indicates that one entity is acting against or resisting another entity or its goals without that opposition being openly known or acknowledged.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e37159688190a6896d9730214ba8 |
completed | April 20, 2026, 8:27 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:04 p.m.