Triple
T8022386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Group Policy |
E186767
|
entity |
| Predicate | defaultRefreshOffset |
P4824
|
FINISHED |
| Object | 30 minutes |
—
|
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: 30 minutes | Statement: [Group Policy, defaultRefreshOffset, 30 minutes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defaultRefreshOffset Context triple: [Group Policy, defaultRefreshOffset, 30 minutes]
-
A.
refreshType
Indicates the manner or category of update applied to an entity, such as whether it is a full, partial, or incremental refresh.
-
B.
usesOffsetFrom
chosen
Indicates that one entity determines or expresses its position, value, or behavior relative to another by applying a specified offset from that reference.
-
C.
previousUTCOffset
Indicates the UTC time offset that applied to an entity (such as a timezone or location) immediately before the current or given offset.
-
D.
timeOffsetReference
Indicates that a temporal value is specified relative to a particular reference time or event, defining the offset between them.
-
E.
dstOffsetSameAsStandard
Indicates that the daylight saving time offset is the same as the standard (non-daylight-saving) time offset.
- 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_69ca82ac7fc081909b1398cf025423af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3e8eab9c81908098e6b17957316c |
completed | March 31, 2026, 3:25 a.m. |
| PD | Predicate disambiguation | batch_69cb049253d08190bafcecfde493ab8b |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:21 p.m.