Triple
T21974401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kwangmyong |
E542667
|
entity |
| Predicate | policyOnEncryption |
P73638
|
FINISHED |
| Object | tightly restricted |
—
|
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: tightly restricted | Statement: [Kwangmyong, policyOnEncryption, tightly restricted]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyOnEncryption Context triple: [Kwangmyong, policyOnEncryption, tightly restricted]
-
A.
protectionPolicy
chosen
Indicates that one entity establishes or enforces rules or measures to safeguard another entity from harm, loss, or risk.
-
B.
requiresEncryption
Indicates that one entity must use encryption when communicating with, storing data for, or otherwise interacting with another entity.
-
C.
dataIsEncrypted
Indicates that the referenced data is stored or transmitted in an encrypted form rather than in plaintext.
-
D.
encryptionIs
Indicates that one entity serves as the encryption method, state, or property applied to another entity.
-
E.
usesEncryptionAlgorithm
Indicates that one entity applies or relies on a specific encryption algorithm to protect data or communications.
- 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12487a1a88190abb8a51fcd533b6a |
completed | April 28, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:03 p.m.