Triple
T31847714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows Backup |
E812984
|
entity |
| Predicate | storesBackupsOn |
P8611
|
FINISHED |
| Object | local hard drive |
—
|
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: local hard drive | Statement: [Windows Backup, storesBackupsOn, local hard drive]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: storesBackupsOn Context triple: [Windows Backup, storesBackupsOn, local hard drive]
-
A.
backsUp
Indicates that one entity provides support, reinforcement, or confirmation for another entity’s actions, statements, or position.
-
B.
backupCommander
Indicates that one entity serves as the designated backup or alternate commander for another entity.
-
C.
storageOption
chosen
Indicates how or where something is stored, specifying the chosen method, medium, or configuration for its storage.
-
D.
storesInterfaceIn
Indicates that one entity keeps or maintains an interface definition within another entity (such as a container, module, or storage location).
-
E.
servesAsBackupFor
Indicates that one entity functions as a substitute or fallback that can take over the role or responsibilities of another entity if needed.
- 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_69f348eb327881909b4584b925742f6e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b037fb0c81909f65de547ea3a5d8 |
completed | May 3, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:50 p.m.