Triple
T27357785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matla Power Station |
E685733
|
entity |
| Predicate | fuelSourceRegion |
P410
|
FINISHED |
| Object | nearby coal mines in Mpumalanga |
—
|
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: nearby coal mines in Mpumalanga | Statement: [Matla Power Station, fuelSourceRegion, nearby coal mines in Mpumalanga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fuelSourceRegion Context triple: [Matla Power Station, fuelSourceRegion, nearby coal mines in Mpumalanga]
-
A.
sourceRegion
chosen
Indicates the geographic or spatial region from which something originates or is derived.
-
B.
energyRegion
Indicates a relationship where a specified region is characterized or defined in terms of its energy properties, levels, or distribution.
-
C.
fuelSupplier
Indicates that one entity supplies fuel to another as a provider in a fuel-related relationship.
-
D.
isMajorSourceOfElectricityFor
Indicates that one entity provides the primary or dominant share of electrical power used by another entity.
-
E.
powerPlantFuel
Indicates that a power plant uses a particular fuel type as its energy source.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62c20321481908ba574ad96d93013 |
completed | May 2, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 11:52 a.m.