Triple
T10000896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heavy Airlift Wing |
E197321
|
entity |
| Predicate | providesCapabilityFor |
P32748
|
FINISHED |
| Object | NATO member states |
—
|
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: NATO member states | Statement: [Heavy Airlift Wing, providesCapabilityFor, NATO member states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesCapabilityFor Context triple: [Heavy Airlift Wing, providesCapabilityFor, NATO member states]
-
A.
providesCapabilityTo
chosen
Indicates that one entity enables or equips another entity with a specific capability or functionality.
-
B.
definesCapability
Indicates that one entity specifies or establishes the abilities, functions, or capacities that another entity can possess or perform.
-
C.
isPartOfCapability
Indicates that one capability is a component or sub-function within a broader, composite capability.
-
D.
integratesCapability
Indicates that one entity incorporates or combines another entity’s capability into its own functionality.
-
E.
demonstratedCapability
Indicates that an entity has shown, through evidence or performance, the ability to carry out a specific action or function.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc8f50888190b2f1c5240cb58e4f |
completed | April 2, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69cd1da2cf9081908a6c0eb5247d0bc2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:51 p.m.