Triple
T36519212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Corridor road network |
E900130
|
entity |
| Predicate | connectsLandlockedCountryToSea |
P199626
|
FINISHED |
| Object | Uganda |
—
|
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: Uganda | Statement: [Northern Corridor road network, connectsLandlockedCountryToSea, Uganda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsLandlockedCountryToSea Context triple: [Northern Corridor road network, connectsLandlockedCountryToSea, Uganda]
-
A.
connectsLandlockedCountryToSeaAccess
chosen
Indicates that something provides a transportation or infrastructural link giving a landlocked country access to the sea.
-
B.
hasLandBorderWithSea
Indicates that an entity’s land area directly borders or touches a sea along its coastline.
-
C.
hasMaritimeConnection
Indicates a relationship in which an entity is linked to seas, oceans, or maritime activities, such as shipping, navigation, or coastal operations.
-
D.
connectsPeninsulaTo
Indicates a relationship where a geographic feature or structure links a peninsula to another landmass or area.
-
E.
hasCoastlineOn
Indicates that one entity’s coastline borders or is directly adjacent to a specified body of water.
- 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_69f76e5eedb88190a393b8c623f71dd7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffada24d188190a576a02dc280a7fb |
completed | May 9, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69ffad46d6ac819081772f408b1389d5 |
completed | May 9, 2026, 9:55 p.m. |
Created at: May 3, 2026, 4:11 p.m.