Triple
T16268296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somalia–Ethiopia border |
E394929
|
entity |
| Predicate | crossesEthnicRegion |
P31352
|
FINISHED |
| Object | Somali-inhabited territories |
—
|
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: Somali-inhabited territories | Statement: [Somalia–Ethiopia border, crossesEthnicRegion, Somali-inhabited territories]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossesEthnicRegion Context triple: [Somalia–Ethiopia border, crossesEthnicRegion, Somali-inhabited territories]
-
A.
crossesRegion
Indicates that an entity moves through or passes across the spatial extent of a specified region.
-
B.
crossBorderRegion
chosen
Indicates a region that spans or intersects the boundary between two or more distinct territorial or jurisdictional areas.
-
C.
hasEthnicDivision
Indicates that a group, region, or entity is characterized by internal divisions or distinctions based on ethnicity.
-
D.
sharesEthnicity
Indicates that two entities belong to the same ethnic group or share the same ethnic background.
-
E.
crossesPoliticalEntity
Indicates that one entity extends over or passes through the territorial boundaries of a political entity (such as a country, state, or province).
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245ca5c708190a1e98ab37740c032 |
completed | April 17, 2026, 2:38 p.m. |
| PD | Predicate disambiguation | batch_69e219f259e88190bf49d8408c04178e |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:05 a.m.