Triple
T2320036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shortgrass prairie |
E51158
|
entity |
| Predicate | receivesAnnualPrecipitation |
P472
|
FINISHED |
| Object | 250–500 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: 250–500 millimeters | Statement: [Shortgrass prairie, receivesAnnualPrecipitation, 250–500 millimeters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivesAnnualPrecipitation Context triple: [Shortgrass prairie, receivesAnnualPrecipitation, 250–500 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.
isOneOfRainiestCitiesInCanada
Indicates that a city ranks among the locations in Canada with the highest amount or frequency of rainfall.
-
E.
hasSeasonalFlooding
Indicates that an area regularly experiences flooding during specific, recurring times of the year.
- 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_69a88b074b908190ae983dbca7757d88 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc685f05481909c863b29d1f6bacd |
completed | March 7, 2026, 6:32 a.m. |
| PD | Predicate disambiguation | batch_69abc5909cc48190aab257313542dc49 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:49 p.m.