Triple
T25276216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern African rail network |
E633701
|
entity |
| Predicate | majorPortConnection |
P942
|
FINISHED |
| Object | Port of Durban |
E103926
|
NE 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: Port of Durban | Statement: [Southern African rail network, majorPortConnection, Port of Durban]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorPortConnection Context triple: [Southern African rail network, majorPortConnection, Port of Durban]
-
A.
portConnections
Indicates that there exists a connection or linkage between two ports or interfaces.
-
B.
connectsMajorHub
Indicates that one entity serves as a link or route between major hubs or primary nodes in a network.
-
C.
hasPortConnection
Indicates that one entity is linked to another via a port or interface through which data, power, or signals can be transmitted.
-
D.
connectionPort
Indicates a specific port through which two components, systems, or devices are connected or can communicate.
-
E.
hasMajorPort
chosen
Indicates that a location possesses a primary, significant seaport used for major commercial or transportation activities.
- F. None of above.
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_69e75a92f48881909974ff9c11150a2e |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a11271e15f08190a6f8526fa979c19b |
completed | May 23, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 21, 2026, 1:17 p.m.