Triple
T32143204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PMC Wagner |
E820960
|
entity |
| Predicate | allegedFinancier |
P181358
|
FINISHED |
| Object | Yevgeny Prigozhin |
—
|
NE NERFINISHED |
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: Yevgeny Prigozhin | Statement: [PMC Wagner, allegedFinancier, Yevgeny Prigozhin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allegedFinancier Context triple: [PMC Wagner, allegedFinancier, Yevgeny Prigozhin]
-
A.
allegedAgentOf
Indicates that one entity is claimed or suspected, but not confirmed, to be the agent responsible for an action or event involving another entity.
-
B.
allegedActor
Indicates that the subject is claimed or accused to be the actor responsible for a particular action or event, without confirming that the claim is true.
-
C.
allegedOrganization
Indicates that an entity is claimed or suspected to be an organization, without confirming that the claim is true.
-
D.
allegedImpostor
Indicates that one entity is claimed or suspected to be fraudulently posing as another entity.
-
E.
allegedLeaderOf
Indicates that one entity is claimed or suspected, but not definitively established, to be the leader of another entity or group.
- F. None of above. chosen
Provenance (4 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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
| PDg | Predicate description generation | batch_69f7688cea58819098bdfd7c80df7634 |
completed | May 3, 2026, 3:23 p.m. |
Created at: May 1, 2026, 12:31 a.m.