Triple
T34219111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ethiopia–Djibouti border |
E877875
|
entity |
| Predicate | connectsLandlockedCountryToSeaAccess |
P199626
|
FINISHED |
| Object | Ethiopia |
—
|
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: Ethiopia | Statement: [Ethiopia–Djibouti border, connectsLandlockedCountryToSeaAccess, Ethiopia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsLandlockedCountryToSeaAccess Context triple: [Ethiopia–Djibouti border, connectsLandlockedCountryToSeaAccess, Ethiopia]
-
A.
hasMaritimeConnection
Indicates a relationship in which an entity is linked to seas, oceans, or maritime activities, such as shipping, navigation, or coastal operations.
-
B.
hasSeaRouteConnection
Indicates that there exists a navigable maritime route linking two locations or entities.
-
C.
hasLandBorderWithSea
Indicates that an entity’s land area directly borders or touches a sea along its coastline.
-
D.
connectsInlandCityToCoast
Indicates a relationship where a route, link, or infrastructure connects an inland city to a coastal area or city.
-
E.
connectsInlandToBorder
Indicates that an inland location is linked or provides a route to a border location.
- 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_69f349b0b4bc819088c1552424089ee9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff49016dcc8190a8a43868c728b4f1 |
completed | May 9, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69ff4891924c8190b5be340e2520e012 |
completed | May 9, 2026, 2:45 p.m. |
| PDg | Predicate description generation | batch_69ff490096388190832a90e9abbc8d81 |
completed | May 9, 2026, 2:47 p.m. |
Created at: May 1, 2026, 1:55 a.m.