Triple
T11655739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows Certificate Store |
E277007
|
entity |
| Predicate | supportsKeyStorage |
P100213
|
FINISHED |
| Object | software key storage |
—
|
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: software key storage | Statement: [Windows Certificate Store, supportsKeyStorage, software key storage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsKeyStorage Context triple: [Windows Certificate Store, supportsKeyStorage, software key storage]
-
A.
supportsKeyManagementProtocol
Indicates that one entity is capable of using or is compatible with a specified key management protocol for handling cryptographic keys.
-
B.
supportsBlockStorage
Indicates that one entity provides or is compatible with block-level storage capabilities for another entity.
-
C.
supportsKeyLength
Indicates that one entity is capable of handling, accepting, or operating with a specified cryptographic key length associated with another entity.
-
D.
supportsViewingKeys
Indicates that an entity enables or allows access to viewing keys associated with another entity or resource.
-
E.
supportsKeyboard
Indicates that one entity is compatible with or able to be operated using a keyboard as an input method.
- 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_69d6aafbb3c081908a9cdb4ecb8d981d |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a3cee010819089cffdbefe5a6efb |
completed | April 10, 2026, 7:16 a.m. |
| PD | Predicate disambiguation | batch_69d85ddc780481909a3bc63832fe2bd2 |
completed | April 10, 2026, 2:18 a.m. |
| PDg | Predicate description generation | batch_69d87f30642c8190ad94fa061cde186b |
completed | April 10, 2026, 4:40 a.m. |
Created at: April 8, 2026, 9:39 p.m.