Triple
T10085613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 611th Air Communications Squadron |
E215211
|
entity |
| Predicate | supportsInstallationType |
P24486
|
FINISHED |
| Object | air bases |
—
|
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: air bases | Statement: [611th Air Communications Squadron, supportsInstallationType, air bases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsInstallationType Context triple: [611th Air Communications Squadron, supportsInstallationType, air bases]
-
A.
supportsInstallation
Indicates that one entity is capable of enabling, handling, or being compatible with the installation of another entity.
-
B.
supportsInstallationMedia
Indicates that one entity is capable of accepting, handling, or working with a specified type of installation media for setup or deployment purposes.
-
C.
requiresInstallation
Indicates that one entity must be installed or set up before the other can be used or become operational.
-
D.
supportsType
chosen
Indicates that one entity is capable of handling, accepting, or being compatible with a specified type.
-
E.
supportsTestType
Indicates that one entity is capable of handling, executing, or being compatible with a specified type of test.
- 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_69ca83a1eed081908b2e9580f2ebeea7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd04609748190987a9364a387fa61 |
completed | April 2, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69cd4b97870481908f7a89df10d58a9e |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9 p.m.