Triple
T21940612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BRT |
E541808
|
entity |
| Predicate | previouslyHadDSTVariant |
P6183
|
FINISHED |
| Object | BRST |
—
|
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: BRST | Statement: [BRT, previouslyHadDSTVariant, BRST]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previouslyHadDSTVariant Context triple: [BRT, previouslyHadDSTVariant, BRST]
-
A.
previouslyObservedDST
Indicates that the subject has been observed in a context where daylight saving time (DST) was in effect at some point in the past.
-
B.
hasHistoricalPermanentDSTExperiment
Indicates that an entity has undergone a historically significant, long-term or permanent daylight saving time experiment or trial.
-
C.
DSTNotRegularSince
Indicates that daylight saving time has not been regularly observed in the specified location since a given point in time.
-
D.
usesDSTNotationChange
Indicates that a system or context applies a change in notation or representation when switching between standard time and daylight saving time.
-
E.
hasDaylightSavingVariant
chosen
Indicates that one time-related entity is the daylight saving time version or counterpart of another standard-time entity.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12420b1cc81909b375891aedc0979 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:55 p.m.