Triple
T5770730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SIPRNET |
E127324
|
entity |
| Predicate | supportsClassificationUpTo |
P66321
|
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, supportsClassificationUpTo, Secret]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsClassificationUpTo Context triple: [SIPRNET, supportsClassificationUpTo, Secret]
-
A.
supportedClass
Indicates that one entity is a class or type that is recognized, handled, or operable within the capabilities or context provided by another entity.
-
B.
isClassifiedUnder
Indicates that one entity is categorized or grouped within a broader class, type, or category represented by another entity.
-
C.
definesClassification
Indicates that one entity specifies or establishes the classification or category to which another entity belongs.
-
D.
usesClassifiers
Indicates that one entity employs or relies on a system of classifiers (such as category labels or measure words) when referring to or organizing another entity.
-
E.
hasUCIClassification
Indicates that an entity is assigned a specific classification according to the UCI (Union Cycliste Internationale) categorization system.
- 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_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. |
| PDg | Predicate description generation | batch_69c02ac9603481909e3fa295d7904a15 |
completed | March 22, 2026, 5:45 p.m. |
Created at: March 22, 2026, 3:50 p.m.