Triple
T5479197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Security Policy Database |
E123428
|
entity |
| Predicate | policyDecisionPointFor |
P64002
|
FINISHED |
| Object | IPsec packet handling |
—
|
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: IPsec packet handling | Statement: [Security Policy Database, policyDecisionPointFor, IPsec packet handling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyDecisionPointFor Context triple: [Security Policy Database, policyDecisionPointFor, IPsec packet handling]
-
A.
decisionPublicationPolicy
Indicates the policy or rules governing how decisions are made public or communicated.
-
B.
policyElement
Indicates that something is a component or constituent part of a broader policy.
-
C.
policySource
Indicates the origin or authority from which a given policy is derived or issued.
-
D.
policyStoredIn
Indicates that a policy is kept or maintained within a particular storage location or system.
-
E.
decisionPublication
Indicates that a decision has been formally published or made publicly available.
- F. None of above. chosen
Provenance (4 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_69bd4648883481909e9775d43300c5fa |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd9247a16c8190ac5a02534da48853 |
completed | March 20, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69bd91a58c448190904964a439045e05 |
completed | March 20, 2026, 6:27 p.m. |
| PDg | Predicate description generation | batch_69bd9214b8488190979112c7615f359a |
completed | March 20, 2026, 6:29 p.m. |
Created at: March 20, 2026, 2:09 p.m.