Triple
T8298496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chari River |
E194283
|
entity |
| Predicate | percentageOfLakeChadInflow |
P31964
|
FINISHED |
| Object | about 90% |
—
|
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 90% | Statement: [Chari River, percentageOfLakeChadInflow, about 90%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentageOfLakeChadInflow Context triple: [Chari River, percentageOfLakeChadInflow, about 90%]
-
A.
inlandWaterPercentage
Indicates the proportion of a geographic area’s total surface that is covered by inland water bodies such as lakes, rivers, and reservoirs.
-
B.
areaWaterPercentage
Indicates the proportion of an entity’s total area that is covered by water, typically expressed as a percentage.
-
C.
inflowWatercourse
Indicates that one watercourse flows into or feeds another water body or watercourse.
-
D.
receivesFreshwaterFrom
chosen
Indicates that one entity is supplied with or obtains freshwater from another entity as its source.
-
E.
drainagePercentageOfUS
Indicates the proportion of the total area of the United States that is drained by a given water body or drainage system.
- 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_69ca82e50ebc81909aa7b260c76bd757 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7dfa040c8190ab801b3910e39142 |
completed | March 31, 2026, 7:55 a.m. |
| PD | Predicate disambiguation | batch_69cb70b5b5348190b296e0ecec95de60 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 5:53 p.m.