Triple
T34093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Partnership for Peace countries |
E678
|
entity |
| Predicate | engageIn |
P81
|
FINISHED |
| Object | defence reform cooperation with NATO |
—
|
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: defence reform cooperation with NATO | Statement: [Partnership for Peace countries, engageIn, defence reform cooperation with NATO]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: engageIn Context triple: [Partnership for Peace countries, engageIn, defence reform cooperation with NATO]
-
A.
involves
Indicates that an entity participates in, is a part of, or is implicated within a particular event, process, or relationship.
-
B.
activity
chosen
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
C.
notableEngagement
Indicates a significant interaction, involvement, or participation between entities that is noteworthy or distinguished in some context.
-
D.
meets
Indicates that two or more entities come together at the same place and time, typically for interaction or a shared purpose.
-
E.
convenes
Indicates bringing people or groups together to formally meet, discuss, or deliberate on a particular matter.
- 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a2490019948190a89bb0910c60d462 |
completed | Feb. 28, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69a24872e4e481908567850168d65015 |
completed | Feb. 28, 2026, 1:44 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.