Triple
T19105713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Дмитрий Андреевич Муратов |
E467647
|
entity |
| Predicate | связан с темой |
P107052
|
FINISHED |
| Object | убийства журналистов «Новой газеты» |
—
|
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: убийства журналистов «Новой газеты» | Statement: [Дмитрий Андреевич Муратов, связан с темой, убийства журналистов «Новой газеты»]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: связан с темой Context triple: [Дмитрий Андреевич Муратов, связан с темой, убийства журналистов «Новой газеты»]
-
A.
associatedWithWorkTheme
Indicates a relationship where something is connected or related to a particular work theme or subject matter.
-
B.
associatedWithSubject
chosen
Indicates a general relationship or connection between an entity and a subject, without specifying the exact nature of that association.
-
C.
関連主題
Indicates that there exists a thematically or contextually related subject connected to the given entity.
-
D.
majorThemeAssociation
Indicates that one entity is associated with another as a primary or central theme.
-
E.
associatedThemeElements
Indicates a relationship where certain elements are linked to, or grouped under, a particular theme as its related components.
- 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.