Triple
T34219109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ethiopia–Djibouti border |
E877875
|
entity |
| Predicate | crossesHomelandOf |
P187410
|
FINISHED |
| Object | Afar people |
—
|
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: Afar people | Statement: [Ethiopia–Djibouti border, crossesHomelandOf, Afar people]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossesHomelandOf Context triple: [Ethiopia–Djibouti border, crossesHomelandOf, Afar people]
-
A.
crossesBorderOf
Indicates that one entity passes from one side of the boundary of another entity (typically a region or area) to the other side, traversing its border.
-
B.
hasHomeland
Indicates that an entity considers or recognizes a particular place or region as its homeland or place of origin.
-
C.
crossesInternationalBoundaryAt
Indicates that one entity passes from one country’s territory into another at a specific boundary location.
-
D.
crossesStateBorders
Indicates that the referenced entity extends into or passes through more than one state’s territorial boundaries.
-
E.
wasHomelandIn
Indicates that a location historically served as the homeland or place of origin for a specified group or entity.
- 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_69fb563aec448190875410fb1a3ed624 |
completed | May 6, 2026, 2:54 p.m. |
| PD | Predicate disambiguation | batch_69fb35b9ede881908aaae93a215525df |
completed | May 6, 2026, 12:36 p.m. |
| PDg | Predicate description generation | batch_69fb563a28d88190b28345c465c545f8 |
completed | May 6, 2026, 2:54 p.m. |
Created at: May 1, 2026, 1:55 a.m.