Triple
T14664783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bamako–Dakar Railway |
E344338
|
entity |
| Predicate | enablesAccess |
P51771
|
FINISHED |
| Object | Atlantic Ocean trade routes |
—
|
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: Atlantic Ocean trade routes | Statement: [Bamako–Dakar Railway, enablesAccess, Atlantic Ocean trade routes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enablesAccess Context triple: [Bamako–Dakar Railway, enablesAccess, Atlantic Ocean trade routes]
-
A.
controlsAccessTo
Indicates that one entity regulates, manages, or determines the ability of another entity to reach, use, or interact with a resource, location, or service.
-
B.
accessProvides
chosen
Indicates that one entity grants or enables the ability to use, enter, or retrieve another entity or resource.
-
C.
accessIs
Indicates that one entity has the ability, permission, or means to reach, use, or interact with another entity or resource.
-
D.
accessibleOn
Indicates that one entity can be reached, used, or obtained through another entity (such as a platform, device, or medium).
-
E.
accessFeature
Indicates that one entity is permitted to use or interact with a specific feature or capability of 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_69d822e283fc8190a0e4c235cf880052 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb54c69f8819080a37161deecfba8 |
completed | April 14, 2026, 9:44 p.m. |
| PD | Predicate disambiguation | batch_69de6576f0208190aa94d995e797ac38 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:27 a.m.