Triple
T22630634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KST |
E558538
|
entity |
| Predicate | offsetFromKSTToUTC |
P43573
|
FINISHED |
| Object | −9 hours |
—
|
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 hours | Statement: [KST, offsetFromKSTToUTC, −9 hours]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offsetFromKSTToUTC Context triple: [KST, offsetFromKSTToUTC, −9 hours]
-
A.
offsetFromKoreaStandardTime
chosen
Indicates the time difference between a given time reference and Korea Standard Time (KST), typically expressed as an offset in hours or minutes.
-
B.
offsetFromJapanStandardTime
Indicates the time difference between a given time zone or time value and Japan Standard Time (JST), typically expressed as an offset in hours or minutes.
-
C.
offsetFromJapanStandardTimeHours
Indicates the number of hours by which a time value is ahead of or behind Japan Standard Time.
-
D.
offsetFromUTC
Indicates the time difference between a given time value and Coordinated Universal Time (UTC), typically expressed as an offset in hours and/or minutes.
-
E.
offsetInSecondsFromUTC
Indicates the time difference, measured in whole seconds, between a given time reference and Coordinated Universal Time (UTC).
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17008e7648190b243c18067b4efb9 |
completed | April 29, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_69ee62855558819080da946c7b35a160 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 3:02 p.m.