Triple
T28391034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows Prefetch |
E719155
|
entity |
| Predicate | storesDataInDirectory |
P1596
|
FINISHED |
| Object | C:\Windows\Prefetch |
—
|
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: C:\Windows\Prefetch | Statement: [Windows Prefetch, storesDataInDirectory, C:\Windows\Prefetch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: storesDataInDirectory Context triple: [Windows Prefetch, storesDataInDirectory, C:\Windows\Prefetch]
-
A.
dataStorage
chosen
Indicates a relationship where one entity serves as a repository that holds, retains, or maintains data for another entity or process.
-
B.
storesInterfaceIn
Indicates that one entity keeps or maintains an interface definition within another entity (such as a container, module, or storage location).
-
C.
storesDataType
Indicates that an entity is designed to hold, manage, or persist information of a specified data type.
-
D.
storageOrgan
Indicates that one entity serves as a storage organ (a specialized structure for storing substances like nutrients or water) for another entity.
-
E.
storesVersionedFilesIn
Indicates that an entity keeps and manages files in a location or system where multiple versions of those files are stored and tracked over time.
- 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_69eff6ef211081909d31d9be5f5567e6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6617ba4a88190bfc5c305acb4f93f |
completed | May 2, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 1:13 a.m.