Triple
T946688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sahel |
E20427
|
entity |
| Predicate | averageAnnualRainfallRange |
P472
|
FINISHED |
| Object | about 150–600 millimeters |
—
|
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: about 150–600 millimeters | Statement: [Sahel, averageAnnualRainfallRange, about 150–600 millimeters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averageAnnualRainfallRange Context triple: [Sahel, averageAnnualRainfallRange, about 150–600 millimeters]
-
A.
averageAnnualPrecipitation
chosen
Indicates the typical total amount of precipitation an entity receives over the course of a year, averaged across multiple years.
-
B.
averageAnnualSnowfall
Indicates the typical amount of snow that falls in a given location over the course of a year, averaged across multiple years.
-
C.
averageAnnualSunshineDays
Indicates the typical number of days per year that a location experiences sunshine, averaged over a specified period.
-
D.
averageTemperature
Indicates the typical or mean temperature value associated with an entity over a specified period or context.
-
E.
hasExtremeWeatherCharacteristic
Indicates that something possesses a notable or defining feature related to extreme weather conditions.
- 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_69a493b0f2fc81908cd227480a5356a1 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3bcad2481908b83575b2fb80d14 |
completed | March 1, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69a4b29f05f481908814bd11f235e9d0 |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.