Triple
T9803373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wagner Group |
E237893
|
entity |
| Predicate | usesRecruitmentSource |
P4145
|
FINISHED |
| Object | Russian prisons |
—
|
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: Russian prisons | Statement: [Wagner Group, usesRecruitmentSource, Russian prisons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesRecruitmentSource Context triple: [Wagner Group, usesRecruitmentSource, Russian prisons]
-
A.
recruitmentFrom
chosen
Indicates that one entity recruits or sources members, employees, or participants from another entity.
-
B.
recruitmentControlledBy
Indicates that the process of recruiting or selecting members for a group, role, or organization is directed, managed, or determined by a particular controlling entity.
-
C.
usesSourceType
Indicates that one entity makes use of, relies on, or operates based on a particular type or category of source.
-
D.
recruitedAs
Indicates that one entity has been brought into a role, position, or organization by another through a recruitment process.
-
E.
personnelSource
Indicates the origin or provider from which personnel are obtained or assigned.
- 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab78832481909b184b21a8a46e50 |
completed | April 1, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.