Triple
T30626794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umkhosi woMhlanga |
E779602
|
entity |
| Predicate | hasPrimaryProvince |
P79153
|
FINISHED |
| Object | KwaZulu-Natal |
—
|
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: KwaZulu-Natal | Statement: [Umkhosi woMhlanga, hasPrimaryProvince, KwaZulu-Natal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryProvince Context triple: [Umkhosi woMhlanga, hasPrimaryProvince, KwaZulu-Natal]
-
A.
hasMajorProvince
Indicates that an entity possesses or is associated with a primary or most significant province within a larger territorial or administrative context.
-
B.
hasProvinceOrRegion
Indicates that one entity includes, is associated with, or is located within a specific province or region as an administrative or geographic subdivision.
-
C.
hasPrimaryNation
Indicates that one entity is designated as the main or principal nation associated with another entity.
-
D.
hasHomeProvinceOrState
chosen
Indicates that an entity is associated with a particular province or state as its home or primary regional location.
-
E.
hasProvinceEquivalent
Indicates that one administrative division is equivalent in status or function to a province within a given political or territorial system.
- 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_69f224a431548190a44ad9d088dbf91f |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fffc783b648190bcd7df017514d206 |
completed | May 10, 2026, 3:33 a.m. |
| PD | Predicate disambiguation | batch_69fffc03fa24819099e12413dc6e0afd |
completed | May 10, 2026, 3:31 a.m. |
Created at: April 29, 2026, 8:28 p.m.