Triple
T28393976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African telephone numbering plan |
E719233
|
entity |
| Predicate | numberingFormat |
P181640
|
FINISHED |
| Object | closed numbering plan |
—
|
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: closed numbering plan | Statement: [South African telephone numbering plan, numberingFormat, closed numbering plan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberingFormat Context triple: [South African telephone numbering plan, numberingFormat, closed numbering plan]
-
A.
hasNumberingFormat
chosen
Indicates that an entity uses or is associated with a particular scheme or style for numbering items, elements, or positions.
-
B.
cellFormat
Indicates how the visual presentation or styling (such as font, color, borders, or number format) is applied to a cell in a structured layout or table.
-
C.
numberingType
Indicates the scheme or style used to assign sequential numbers or labels within an ordered set.
-
D.
numberForm
Indicates that one entity is a representation or written form of a numerical value associated with another entity.
-
E.
numberingDirection
Indicates the direction or order in which items are sequentially numbered within a set or structure.
- 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_69ff6c061c6c81909ff485e9cafc88a2 |
completed | May 9, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69ff6aaf886c8190a3c87d089453f3de |
completed | May 9, 2026, 5:11 p.m. |
Created at: April 28, 2026, 1:15 a.m.