Triple
T31582877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows NT security model |
E805871
|
entity |
| Predicate | accessTokenContains |
P177027
|
FINISHED |
| Object | user SID |
—
|
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: user SID | Statement: [Windows NT security model, accessTokenContains, user SID]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessTokenContains Context triple: [Windows NT security model, accessTokenContains, user SID]
-
A.
tokenClaim
chosen
Indicates that an entity asserts ownership of, or entitlement to, a specific token or set of tokens.
-
B.
tokenAudience
Indicates the intended group or recipients for whom a particular token (such as a digital asset, credential, or access right) is designed or targeted.
-
C.
bearerInstanceOf
Indicates that a bearer (such as an agent, object, or entity) is an instance or specific realization of a more general class, type, or role.
-
D.
accessIs
Indicates that one entity has the ability, permission, or means to reach, use, or interact with another entity or resource.
-
E.
authorizationCheck
Indicates that a verification is performed to determine whether an entity has the required permissions to perform a specific action or access a particular resource.
- 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_69f348d3a86c8190a3e5e539a4dd125f |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f7221dc9a88190bb8194fcc29c42bc |
completed | May 3, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f72153a9188190b02adc84e1be4af8 |
completed | May 3, 2026, 10:20 a.m. |
Created at: April 30, 2026, 10:24 p.m.