Triple
T5770729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SIPRNET |
E127324
|
entity |
| Predicate | securityClassificationLevel |
P406
|
FINISHED |
| Object | Secret |
—
|
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: Secret | Statement: [SIPRNET, securityClassificationLevel, Secret]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securityClassificationLevel Context triple: [SIPRNET, securityClassificationLevel, Secret]
-
A.
securityClassification
chosen
Indicates the level or category of security sensitivity or access restriction assigned to an entity.
-
B.
classificationLevel
Indicates the degree or tier within an ordered system or hierarchy to which something is assigned for categorization or control purposes.
-
C.
governmentClassification
Indicates that an entity is assigned a specific status or category according to a government’s official classification system.
-
D.
disclosureLevel
Indicates the extent or degree to which information is revealed, shared, or made accessible in a given context.
-
E.
protectionLevel
Indicates the degree or extent to which something is safeguarded against harm, risk, or unauthorized access.
- 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_69c00834f6308190851b0abeddd8ed7e |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02acb12c081908e4beee4a957f9f9 |
completed | March 22, 2026, 5:45 p.m. |
| PD | Predicate disambiguation | batch_69c021ce8d3c81909b332cb1c33a61ad |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:50 p.m.