Triple
T34675085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1992 Sochi Agreement |
E890471
|
entity |
| Predicate | createdForceComposition |
P62674
|
FINISHED |
| Object | Russian peacekeeping contingent |
—
|
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 peacekeeping contingent | Statement: [1992 Sochi Agreement, createdForceComposition, Russian peacekeeping contingent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdForceComposition Context triple: [1992 Sochi Agreement, createdForceComposition, Russian peacekeeping contingent]
-
A.
forceComponentCreated
chosen
Indicates that a force-related component has been instantiated or newly created within a system or context.
-
B.
forcesComposition
Indicates that one entity compels or determines the structural makeup or arrangement of another entity.
-
C.
unionForcesComposition
Indicates that multiple forces are combined or aggregated to form a single resultant force.
-
D.
componentForces
Indicates that a force is decomposed into its constituent directional components that together produce the original overall force.
-
E.
generatesForce
Indicates that one entity produces or exerts a physical force on another entity or on its surroundings.
- 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_69f349d9c59481908b36baa0be093aea |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff56ef0a5c8190ae729d66a8cf7fc4 |
completed | May 9, 2026, 3:46 p.m. |
| PD | Predicate disambiguation | batch_69ff539859c481909ec56310da418688 |
completed | May 9, 2026, 3:32 p.m. |
Created at: May 1, 2026, 2:05 a.m.