Triple
T4686257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Durban |
E103926
|
entity |
| Predicate | ISO3166-2Region |
P42695
|
FINISHED |
| Object | ZA-KZN |
—
|
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: ZA-KZN | Statement: [Port of Durban, ISO3166-2Region, ZA-KZN]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ISO3166-2Region Context triple: [Port of Durban, ISO3166-2Region, ZA-KZN]
-
A.
ISO3166-2RegionCode
chosen
Indicates the standardized ISO 3166-2 code that specifies the particular primary administrative subdivision (such as a state, province, or region) to which an entity belongs.
-
B.
ISO3166-2DifferentFrom
Indicates that two ISO 3166-2 subdivision codes are explicitly distinct and should not be considered equivalent or interchangeable.
-
C.
countrySubdivisionStandardLink
Indicates a reference or link to the standard or authoritative specification that defines the country’s internal subdivisions.
-
D.
NUTSRegionCode
Indicates the classification of an entity according to the NUTS (Nomenclature of Territorial Units for Statistics) regional coding system used for statistical regions.
-
E.
subregionCodeFor
Indicates that one entity is the code assigned to identify a specific subregion of the other 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_69bd43debbf08190b4bc372e286ec234 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd66059bfc8190885d26d05dd38df1 |
completed | March 20, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69bd6219da948190bbbb50f08573ab4d |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:16 p.m.