Triple
T25911325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanaga River basin |
E652902
|
entity |
| Predicate | mainLandCover |
P116511
|
FINISHED |
| Object | savanna |
—
|
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: savanna | Statement: [Sanaga River basin, mainLandCover, savanna]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainLandCover Context triple: [Sanaga River basin, mainLandCover, savanna]
-
A.
drainageBasinLandCover
chosen
Indicates the type or characteristics of land cover present within a drainage basin area.
-
B.
forestCoverCharacteristic
Indicates a relationship where a forested area possesses a specific attribute or quality related to its tree or vegetation cover.
-
C.
majorLandUse
Indicates the primary way a given area of land is utilized or designated (e.g., residential, commercial, agricultural).
-
D.
hasLandCoverage
Indicates that a specified area or region is covered or occupied by a particular type of land surface or land use.
-
E.
hasHistoricalLandCover
Indicates that an entity is associated with information about the land cover that existed in a specified area during a past time period.
- 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_69e7ab3d3f8481909bc53ed64c06af33 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f603c5bd048190a8505dd3cef779ed |
completed | May 2, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 22, 2026, 8:28 a.m.