Triple
T10883688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alaska Time |
E256985
|
entity |
| Predicate | hasStandardOffsetHours |
P68829
|
FINISHED |
| Object | −9 |
—
|
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: −9 | Statement: [Alaska Time, hasStandardOffsetHours, −9]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStandardOffsetHours Context triple: [Alaska Time, hasStandardOffsetHours, −9]
-
A.
hasStandardTimeUTCOffset
chosen
Indicates the fixed difference in hours and minutes between an entity’s standard (non-daylight-saving) local time and Coordinated Universal Time (UTC).
-
B.
hasNonIntegerHourOffset
Indicates that the time-related value or time zone differs from a reference time by an offset that is not a whole number of hours (e.g., includes 30- or 45-minute increments).
-
C.
hasTimeOffset
Indicates that one temporal value is shifted or displaced from another by a specified amount of time.
-
D.
timeOffsetInHours
Indicates the temporal difference between two time points or events, measured in hours.
-
E.
isStandardTime
Indicates that a given time value is expressed in standard (non-daylight-saving) time for its associated time zone.
- 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_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d751dc3518819090e03d81ea5c8aa9 |
completed | April 9, 2026, 7:14 a.m. |
| PD | Predicate disambiguation | batch_69d70d3943c881908895397eccc3e415 |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:21 p.m.