Triple
T22027670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TLS-over-TCP |
E544007
|
entity |
| Predicate | canUseCipherSuite |
P32016
|
FINISHED |
| Object | AES-GCM |
—
|
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: AES-GCM | Statement: [TLS-over-TCP, canUseCipherSuite, AES-GCM]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canUseCipherSuite Context triple: [TLS-over-TCP, canUseCipherSuite, AES-GCM]
-
A.
supportsCipherSuite
chosen
Indicates that one entity is capable of using or handling a specified cryptographic cipher suite in secure communications.
-
B.
usesProtocolSuite
Indicates that one entity operates or communicates by employing the set of communication protocols defined by another entity’s protocol suite.
-
C.
cipherSuiteIdentifier
Indicates the specific cryptographic cipher suite used or referenced in a communication or security context.
-
D.
canBeEncryptedUsing
Indicates that one entity is capable of being transformed into a secure, encoded form by applying the encryption method or key represented by another entity.
-
E.
hasCryptUse
Indicates that an entity makes use of cryptographic methods, protocols, or mechanisms in its operation or behavior.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127cdf5c08190ac804664d6e56fe2 |
completed | April 28, 2026, 9:34 p.m. |
| PD | Predicate disambiguation | batch_69e6f63b0d048190b241622759aab9de |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:24 p.m.