Triple
T36619330
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Centre for Medium Range Weather Forecasting |
E903688
|
entity |
| Predicate | timeRangeDefinition |
P302
|
FINISHED |
| Object | 3 to 10 days |
—
|
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: 3 to 10 days | Statement: [National Centre for Medium Range Weather Forecasting, timeRangeDefinition, 3 to 10 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeRangeDefinition Context triple: [National Centre for Medium Range Weather Forecasting, timeRangeDefinition, 3 to 10 days]
-
A.
timePeriod
chosen
Indicates the specific span or interval of time during which an event, state, or relationship occurs or is valid.
-
B.
timePeriodWithin
Indicates that one time period is entirely contained within the bounds of another time period.
-
C.
timePeriodQualifier
Indicates how a time-related statement or value is further specified or constrained, such as by defining its scope, phase, or contextual condition within a broader time period.
-
D.
timePeriodFormulated
Indicates the time period during which something (such as a concept, theory, or plan) was formulated or developed.
-
E.
timeType
Indicates the specific temporal category or classification associated with a time-related entity or value (e.g., duration, point in time, interval, or recurrence type).
- 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_69f76e6960e4819092047756ceb9a17e |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c9f5a8848190ba956ff27f44e396 |
completed | May 3, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f7c8999a348190abc1895eaa6e036d |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:11 p.m.