Triple
T3468579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ACDT |
E73196
|
entity |
| Predicate | typicalDSTStartRule |
P717
|
FINISHED |
| Object | first Sunday in October (varies by legislation) |
—
|
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: first Sunday in October (varies by legislation) | Statement: [ACDT, typicalDSTStartRule, first Sunday in October (varies by legislation)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalDSTStartRule Context triple: [ACDT, typicalDSTStartRule, first Sunday in October (varies by legislation)]
-
A.
DSTStartRule
chosen
Indicates the rule or condition that determines when daylight saving time begins for a given time zone or region.
-
B.
typicalDSTStartMonth
Indicates the month in which daylight saving time typically begins for a given place or jurisdiction.
-
C.
DSTEndRule
Indicates the rule or condition that specifies when daylight saving time ends in a given timekeeping system.
-
D.
typicalDSTEndMonth
Indicates the month in which daylight saving time typically ends for a given region or system.
-
E.
DSTseason
Indicates that the relationship specifies the daylight saving time (DST) period or season during which a time-related event or setting is in effect.
- 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_69ad85b2fed48190948c8765e453d270 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb376d288190abac85f2ffa853dc |
completed | March 8, 2026, 6:08 p.m. |
| PD | Predicate disambiguation | batch_69adae05bb0081909dc7e4779d6e05ef |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:17 p.m.