Triple
T19390801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Souss River |
E485061
|
entity |
| Predicate | drainageBasin |
P1559
|
FINISHED |
| Object | Souss Basin |
—
|
NE NERFINISHED |
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: Souss Basin | Statement: [Souss River, drainageBasin, Souss Basin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Souss Basin Context triple: [Souss River, drainageBasin, Souss Basin]
-
A.
Toshka
Toshka is a region in southern Egypt best known for the Toshka Lakes and large-scale desert reclamation and irrigation projects near Lake Nasser.
-
B.
Souss Tachelhit
Souss Tachelhit is a major regional variety of the Tachelhit Berber language spoken primarily in Morocco’s Souss region.
-
C.
Tanezrouft region
The Tanezrouft region is an extremely arid, sparsely inhabited desert area in the central Sahara, known as one of the hottest and driest places on Earth.
-
D.
Souss-Massa
chosen
Souss-Massa is an administrative region in southwestern Morocco known for its Atlantic coastline, agricultural production, and proximity to the Anti-Atlas mountains.
-
E.
Bassin Agdal
Bassin Agdal is a historic royal water reservoir located within the Agdal Gardens of Marrakech, Morocco.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b44b70c81908e2f0deeabe4360f |
completed | April 20, 2026, 12:25 p.m. |
Created at: April 10, 2026, 1:36 p.m.