Triple
T32143255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PMC Wagner |
E820960
|
entity |
| Predicate | mutinyTarget |
P59854
|
FINISHED |
| Object | Russian Ministry of Defence leadership |
—
|
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: Russian Ministry of Defence leadership | Statement: [PMC Wagner, mutinyTarget, Russian Ministry of Defence leadership]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mutinyTarget Context triple: [PMC Wagner, mutinyTarget, Russian Ministry of Defence leadership]
-
A.
placeOfMutiny
Indicates the location where a mutiny occurred or took place.
-
B.
roleInMutiny
chosen
Indicates that one entity participated in a mutiny with a specific role or capacity in that rebellious action.
-
C.
targetedShip
Indicates that one entity has selected or designated a particular ship as the focus of its attention or action, such as for attack, tracking, or interaction.
-
D.
missionVariant
Indicates a specific version or configuration of a mission that differs from the standard or base mission.
-
E.
sunkAsTarget
Indicates that an entity was sunk specifically in the role of being a target (e.g., during testing, training, or as a deliberate target in an operation).
- 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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b9af93e081908d003dd45258ad27 |
completed | May 3, 2026, 2:57 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a970b0819090c6473844ffa8e3 |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:31 a.m.