Triple
T3012480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chatham Standard Time |
E82253
|
entity |
| Predicate | timeOffsetHours |
P19135
|
FINISHED |
| Object | 12.75 |
—
|
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: 12.75 | Statement: [Chatham Standard Time, timeOffsetHours, 12.75]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOffsetHours Context triple: [Chatham Standard Time, timeOffsetHours, 12.75]
-
A.
timeOffsetType
Indicates the type or category of temporal offset that specifies how one time point is shifted relative to another.
-
B.
timeOffsetReference
Indicates that a temporal value is specified relative to a particular reference time or event, defining the offset between them.
-
C.
hoursAheadOfUTC
chosen
Indicates the number of hours by which a given time or timezone is offset ahead of Coordinated Universal Time (UTC).
-
D.
utcOffsetDescription
Indicates the textual description of how far a time zone’s local time differs from Coordinated Universal Time (UTC), often including details like hours, minutes, and daylight saving adjustments.
-
E.
UTCOffsetDaylightSavingTime
Indicates the time difference from Coordinated Universal Time (UTC) that applies to an entity specifically during daylight saving time periods.
- 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_69ad8b1eb53481908c39bbcd1ec104b2 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a66c334819082d1d320c48eca1b |
completed | March 8, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69ad961a97188190809dc73430a8eda8 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.