Triple
T28394002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African telephone numbering plan |
E719233
|
entity |
| Predicate | premiumRatePrefix |
P148677
|
FINISHED |
| Object | 0862 |
—
|
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: 0862 | Statement: [South African telephone numbering plan, premiumRatePrefix, 0862]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: premiumRatePrefix Context triple: [South African telephone numbering plan, premiumRatePrefix, 0862]
-
A.
premiumRatePrefixExample
Indicates that something serves as an example or template of a prefix used when determining or displaying a premium rate.
-
B.
premiumRateNumbersStartWith
chosen
Indicates that the premium rate numbers begin with a specified prefix or sequence of digits.
-
C.
specialRateNumberPrefixExample
Indicates that an example phone number is provided to illustrate the prefix used for a special-rate number.
-
D.
premiumLevel
Indicates the specific tier or rank of premium status assigned to an entity within a graded or subscription-based system.
-
E.
increasedRateOn
Indicates that one entity has raised the rate, fee, or charge applied to another entity.
- 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_69eff6efd1b08190ae3cefd4f11388a2 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f676c440708190a4b9974e95d2291a |
completed | May 2, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f675fd59608190b246383435e68fce |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 28, 2026, 1:15 a.m.