Triple
T27352921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Witbank coalfield |
E684410
|
entity |
| Predicate | majorConsumer |
P927
|
FINISHED |
| Object | Eskom |
—
|
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: Eskom | Statement: [Witbank coalfield, majorConsumer, Eskom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorConsumer Context triple: [Witbank coalfield, majorConsumer, Eskom]
-
A.
majorUser
Indicates that one user holds a primary, leading, or most significant role or status relative to other users in a given context.
-
B.
majorUse
Indicates that something serves as the primary or most significant use or application of an entity.
-
C.
majorCustomer
chosen
Indicates that one entity is a primary or high-value customer of another entity, typically contributing a significant portion of business or revenue.
-
D.
majorConstituent
Indicates that one entity is a primary or dominant component or part of another entity.
-
E.
majorSee
Indicates that one entity serves as the primary or most important location where another entity is based, operates, or is centered.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fba78aca4c8190b8f1831e8cc04e06 |
completed | May 6, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69fba34a65a4819088bac6c17542d71c |
completed | May 6, 2026, 8:23 p.m. |
Created at: April 27, 2026, 11:49 a.m.