Triple
T31428952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFT |
E801739
|
entity |
| Predicate | isHalfHourOffsetTimeZone |
P15035
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [AFT, isHalfHourOffsetTimeZone, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isHalfHourOffsetTimeZone Context triple: [AFT, isHalfHourOffsetTimeZone, true]
-
A.
isHalfHourTimeZone
chosen
Indicates that a time zone has an offset from Coordinated Universal Time (UTC) that differs by a half-hour increment rather than a whole hour.
-
B.
hasHalfHourOffset
Indicates that one entity’s time zone differs from another’s by an offset that includes a 30-minute (half-hour) component.
-
C.
isWholeHourOffset
Indicates that the time zone or time offset differs from a reference time (typically UTC) by an exact whole number of hours, with no fractional minutes involved.
-
D.
hasUniqueHalfHourDST
Indicates that the entity observes a daylight saving time offset that differs from standard time by a unique half-hour increment rather than a whole hour.
-
E.
usesQuarterHourOffset
Indicates that the time zone or time representation applies a UTC offset that differs from whole hours by a quarter hour (15 minutes).
- 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_69f348c475348190bf579ca858eec77c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a5f71b2c8190aade8a83f465be0c |
completed | May 3, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69f69fe66df08190958558d63ee623d9 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 8:55 p.m.