Triple
T34865293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Lakes refugee crises |
E1004991
|
entity |
| Predicate | refugeeHostCountry |
P39215
|
FINISHED |
| Object | Tanzania |
—
|
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: Tanzania | Statement: [Great Lakes refugee crises, refugeeHostCountry, Tanzania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refugeeHostCountry Context triple: [Great Lakes refugee crises, refugeeHostCountry, Tanzania]
-
A.
countryOfAsylum
chosen
Indicates that one entity serves as the country providing asylum or refuge to another entity.
-
B.
formerHostCountry
Indicates that one entity was previously the host country for another entity, but no longer holds that role.
-
C.
adoptedCountry
Indicates the country that an entity has chosen to reside in or align with as its new home, distinct from its place of origin.
-
D.
countryOfRelocation
Indicates the country to which an entity has moved or been transferred from its original location.
-
E.
lastHostCountry
Indicates the country that most recently hosted a particular event, activity, or entity.
- 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_69f76dbb678081909a247b9b5e1a73ac |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78710282c81909146dc0be91e983f |
completed | May 3, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f784162134819098413482ef52042f |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4 p.m.