Triple
T19145461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngaoundéré railway terminus |
E468666
|
entity |
| Predicate | hasEndpointDirection |
P15156
|
FINISHED |
| Object | north |
—
|
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: north | Statement: [Ngaoundéré railway terminus, hasEndpointDirection, north]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEndpointDirection Context triple: [Ngaoundéré railway terminus, hasEndpointDirection, north]
-
A.
hasDirectionType
Indicates that something possesses or is associated with a specific type or category of direction.
-
B.
hasRouteDirection
chosen
Indicates that a specified route is associated with a particular travel direction (e.g., inbound, outbound, northbound).
-
C.
hasEndpointType
Indicates that an entity has a specific type or classification assigned to one of its endpoints.
-
D.
hasCanalDirection
Indicates that a canal has a specific directional orientation or flow direction relative to a reference.
-
E.
containsDirectionOf
Indicates that one entity includes or encompasses the directional orientation or path associated with another 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e978b0b481909a531efa030c5def |
completed | April 20, 2026, 8:53 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b475d88190a8c15e8eb01dbfef |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:06 p.m.