Triple
T29036768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kassala State |
E737881
|
entity |
| Predicate | hasRefugeePresenceFrom |
P9069
|
FINISHED |
| Object | Eritrea |
—
|
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: Eritrea | Statement: [Kassala State, hasRefugeePresenceFrom, Eritrea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRefugeePresenceFrom Context triple: [Kassala State, hasRefugeePresenceFrom, Eritrea]
-
A.
hasRefugeePopulation
chosen
Indicates that an entity hosts, contains, or is associated with a population of refugees.
-
B.
hasRefugeeStatusRecognizedBy
Indicates that an entity’s refugee status has been formally recognized or granted by a specified authority or organization.
-
C.
hasRefugeeCamp
Indicates that a location or entity hosts, contains, or is the site of a refugee camp.
-
D.
hasRefugeeMovements
Indicates that there are movements or flows of refugees involving the related entities, such as people fleeing from one place and arriving in another.
-
E.
wasRefugee
Indicates that an entity previously lived as a refugee, having been forced to leave their home country due to conflict, persecution, or disaster.
- 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_69f077efb3848190b41574e1670f6ae2 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ffacdf9f5c8190baef0245edfe87fc |
completed | May 9, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69ffac5e86e08190a1e6da0840a237ad |
completed | May 9, 2026, 9:51 p.m. |
Created at: April 28, 2026, 9:59 a.m.