Triple
T18795901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Site W |
E459632
|
entity |
| Predicate | dataClassification |
P7279
|
FINISHED |
| Object | classified information |
—
|
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: classified information | Statement: [Site W, dataClassification, classified information]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataClassification Context triple: [Site W, dataClassification, classified information]
-
A.
securityClassification
Indicates the level or category of security sensitivity or access restriction assigned to an entity.
-
B.
classificationLevel
chosen
Indicates the degree or tier within an ordered system or hierarchy to which something is assigned for categorization or control purposes.
-
C.
authorityResponsibleForClassification
Indicates that a particular authority or organization holds responsibility for determining and assigning the classification of an item or entity.
-
D.
securityClassificationReason
Indicates the justification or basis for assigning a particular security classification to an entity or information.
-
E.
dataSegregation
Indicates that data is kept separate or partitioned so that information from one group, context, or user is not mixed or accessible with that of another.
- 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_69d8d396f54c8190ba49db31e8743842 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a01ed3c08190890d9518ed69fdee |
completed | April 20, 2026, 3:40 a.m. |
| PD | Predicate disambiguation | batch_69e48d16dd34819096e096d0c0e4c15c |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:53 a.m.