Triple
T23233319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Europe/Madrid |
E581219
|
entity |
| Predicate | usesDstRule |
P4879
|
FINISHED |
| Object | European Union DST rules |
—
|
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: European Union DST rules | Statement: [Europe/Madrid, usesDstRule, European Union DST rules]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDstRule Context triple: [Europe/Madrid, usesDstRule, European Union DST rules]
-
A.
usesDSTNotationChange
Indicates that a system or context applies a change in notation or representation when switching between standard time and daylight saving time.
-
B.
hasDst
Indicates that one entity serves as the destination or target location of another entity.
-
C.
DSTPolicy
chosen
Indicates a relationship where a timekeeping system follows a specific daylight saving time policy, defining how and when clocks are adjusted seasonally.
-
D.
usesTimingRules
Indicates that one entity applies or operates according to specified timing rules or constraints in relation to another entity or process.
-
E.
usesUTCOffset
Indicates that one entity applies or relies on the specified UTC time offset for timekeeping or timestamp interpretation.
- 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_69e2460556f88190be1744a84a84173f |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192e70b2c8190abede6e3cd9344f7 |
completed | April 29, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:09 p.m.