Triple
T34219122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ethiopia–Djibouti border |
E877875
|
entity |
| Predicate | givesSeaAccessVia |
P12922
|
FINISHED |
| Object | Port of Djibouti |
—
|
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: Port of Djibouti | Statement: [Ethiopia–Djibouti border, givesSeaAccessVia, Port of Djibouti]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: givesSeaAccessVia Context triple: [Ethiopia–Djibouti border, givesSeaAccessVia, Port of Djibouti]
-
A.
hasSeaAccess
chosen
Indicates that an entity has direct access to the sea, typically via a coastline, port, or navigable waterway connected to the sea.
-
B.
shareSeaAccess
Indicates that two entities have access to the same sea or maritime area, such as sharing a coastline or territorial waters.
-
C.
hasWaterfrontAccessTo
Indicates that one entity is directly adjacent to and can physically access a particular body of water, such as a lake, river, or ocean.
-
D.
hasFishingAccess
Indicates that an entity is permitted or able to fish in or otherwise use a particular water body or fishing area.
-
E.
hasRunwayOrBeachAccess
Indicates that an entity provides direct access to either a runway (for aircraft) or a beach (waterfront), or both.
- 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_69f349b0b4bc819088c1552424089ee9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71080959c81909be22e06eb0bc03d |
completed | May 3, 2026, 9:08 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:55 a.m.