Triple
T30442458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokyo (Narita) – Hong Kong |
E774486
|
entity |
| Predicate | timeZoneOffsetDestination |
P170457
|
FINISHED |
| Object | UTC+08:00 |
—
|
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: UTC+08:00 | Statement: [Tokyo (Narita) – Hong Kong, timeZoneOffsetDestination, UTC+08:00]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeZoneOffsetDestination Context triple: [Tokyo (Narita) – Hong Kong, timeZoneOffsetDestination, UTC+08:00]
-
A.
timeZoneDestination
Indicates the time zone associated with the destination location in a given context or event.
-
B.
timeZoneOriginDST
Indicates that the relationship specifies the original time zone of an entity, including whether daylight saving time (DST) is in effect.
-
C.
timeZoneOffsetOrigin
Indicates the time difference between an entity’s local time and a defined origin or reference time zone.
-
D.
DSTOffsetType
Indicates the relationship between a time reference and the amount of time it is shifted from standard time due to daylight saving time adjustments.
-
E.
timeOffsetType
Indicates the type or category of temporal offset that specifies how one time point is shifted relative to another.
- F. None of above. chosen
Provenance (4 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f69063edbc81909e7735954aabee0b |
completed | May 3, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
| PDg | Predicate description generation | batch_69f68f6584a88190a8c4d95c0c84bee9 |
completed | May 2, 2026, 11:57 p.m. |
Created at: April 29, 2026, 8:08 p.m.