Triple
T16137979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States |
E391582
|
entity |
| Predicate | timeZoneSpan |
P12857
|
FINISHED |
| Object | multiple time zones |
—
|
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: multiple time zones | Statement: [United States, timeZoneSpan, multiple time zones]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeZoneSpan Context triple: [United States, timeZoneSpan, multiple time zones]
-
A.
timeZoneDependence
Indicates how a process, value, or behavior changes or is determined based on the time zone in which it is considered.
-
B.
timeZoneState
Indicates that one entity is a state or region associated with the time zone of another entity.
-
C.
timeZoneType
Indicates the classification or category of a time zone associated with an entity (e.g., standard, daylight, or specific time zone format/type).
-
D.
offsetRangeOfTimeZones
chosen
Indicates that one entity specifies the span or limits of time zone offsets (e.g., from minimum to maximum UTC offsets) applicable to another entity.
-
E.
timeZoneContext
Indicates the time zone setting or context in which an event, action, or relationship is interpreted.
- 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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21a05e68881908319454a478cdda5 |
completed | April 17, 2026, 11:31 a.m. |
| PD | Predicate disambiguation | batch_69e182885bc08190822ae7e8a4b8ac1f |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5:01 a.m.