Triple
T12058374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Air Force bases |
E287100
|
entity |
| Predicate | supportRoleIn |
P10797
|
FINISHED |
| Object | U.S. power projection |
—
|
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: U.S. power projection | Statement: [United States Air Force bases, supportRoleIn, U.S. power projection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportRoleIn Context triple: [United States Air Force bases, supportRoleIn, U.S. power projection]
-
A.
supportsRole
chosen
Indicates that one entity provides the necessary functionality, resources, or conditions for another entity to perform or occupy a specific role.
-
B.
support
Indicates that one entity provides assistance, endorsement, or backing to another entity or its actions.
-
C.
supportStyle
Indicates the manner or approach by which one entity provides assistance or backing to another.
-
D.
providesSupportTo
Indicates that one entity offers help, resources, or reinforcement to another entity to aid its function, stability, or success.
-
E.
supportAgainst
Indicates providing help, resources, or advocacy to oppose or resist a particular target, threat, or adversary.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bda47c8190b94860b31df4a98c |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:47 p.m.