Triple
T28296590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azure Government |
E713584
|
entity |
| Predicate | securityClearedStaff |
P20877
|
FINISHED |
| Object | U.S. persons only |
—
|
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. persons only | Statement: [Azure Government, securityClearedStaff, U.S. persons only]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securityClearedStaff Context triple: [Azure Government, securityClearedStaff, U.S. persons only]
-
A.
authorizedPersonnel
Indicates that the referenced entity is officially permitted or empowered to access, use, or perform actions within a specified system, resource, or context.
-
B.
hasClearance
chosen
Indicates that one entity possesses the required authorization level or permission to access or perform actions on another entity or resource.
-
C.
authorizedMilitaryPersonnel
Indicates that the subject is officially recognized and permitted to perform military duties or access military-restricted areas or resources.
-
D.
maximumAuthorizedPersonnel
Indicates the highest number of personnel that are permitted or authorized for a given role, location, or context.
-
E.
isSecureFacility
Indicates that a facility has protections, controls, and safeguards in place to prevent unauthorized access, tampering, or security breaches.
- 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_69efb524ab688190a1ce7ee7c9520932 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f6b2a65c7c8190ac40f1466ceadefc |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b14d7d508190bc7d4c89dfba4a32 |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 27, 2026, 11:32 p.m.