Triple
T34460770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cape Town–Bulawayo railway |
E884631
|
entity |
| Predicate | operatorCountrySection |
P202763
|
FINISHED |
| Object | Transnet Freight Rail |
—
|
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: Transnet Freight Rail | Statement: [Cape Town–Bulawayo railway, operatorCountrySection, Transnet Freight Rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatorCountrySection Context triple: [Cape Town–Bulawayo railway, operatorCountrySection, Transnet Freight Rail]
-
A.
adminCountry
Indicates that one entity serves as the administrative or governing country for another entity.
-
B.
providerCountry
Indicates the country that serves as the source or origin of the provider in the relationship.
-
C.
countryVariant
Indicates that one entity is a country-specific variant or localized version of another entity.
-
D.
countryService
Indicates that a service, function, or operation is provided by, associated with, or applicable to a specific country.
-
E.
displayedInCountry
Indicates that something is shown, exhibited, or made visible within the boundaries of a specified country.
- F. None of above. chosen
Provenance (4 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_69f349c73a94819094dfcf50d00620b8 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00b6199c348190b1e90375f737d026 |
completed | May 10, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_6a00b5169a7881909a07167c4188731f |
completed | May 10, 2026, 4:40 p.m. |
| PDg | Predicate description generation | batch_6a00b618cb10819095ccef12d8e303c5 |
completed | May 10, 2026, 4:45 p.m. |
Created at: May 1, 2026, 2 a.m.