Triple
T24175014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Mweru |
E599253
|
entity |
| Predicate | catchmentAreaOf |
P4498
|
FINISHED |
| Object | Luapula River |
—
|
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: Luapula River | Statement: [Lake Mweru, catchmentAreaOf, Luapula River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: catchmentAreaOf Context triple: [Lake Mweru, catchmentAreaOf, Luapula River]
-
A.
catchmentArea
Indicates the geographic area from which something (such as a facility, service, or natural feature) draws or collects people, resources, or water.
-
B.
hasCatchmentAreaSize
Indicates the size or extent of the geographic area from which something (e.g., a facility or service) draws its users, resources, or influence.
-
C.
hasCatchmentArea
chosen
Indicates that a geographic or administrative unit serves as the area from which an entity (such as a facility or service) draws its users, resources, or influence.
-
D.
venueArea
Indicates the physical size or spatial extent of a venue, typically measured in units such as square meters or square feet.
-
E.
areaServed
Indicates the geographic region or jurisdiction within which a service, organization, or activity is provided or applicable.
- 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_69e288cca05481908faeb1563711114a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c42f942c8190b103ff29a60fef34 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:34 p.m.