Triple
T32548469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Economy of Burundi |
E831907
|
entity |
| Predicate | hasKeyExportCommodity |
P57094
|
FINISHED |
| Object | arabica coffee |
—
|
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: arabica coffee | Statement: [Economy of Burundi, hasKeyExportCommodity, arabica coffee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyExportCommodity Context triple: [Economy of Burundi, hasKeyExportCommodity, arabica coffee]
-
A.
hasKeyExportVariety
Indicates that an entity has a primary or most important variety specifically intended for export.
-
B.
hasNotableRegionOfExport
Indicates that an entity is associated with a specific geographic region from which it is prominently or significantly exported.
-
C.
importedCommodity
Indicates that a commodity has been brought into a country or region from abroad through import activities.
-
D.
hasExportRestriction
Indicates that an entity is subject to limitations or controls on exporting it to other jurisdictions or parties.
-
E.
exportedGood
chosen
Indicates that a good has been sent out from one country or region to another as part of international trade.
- 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_69f34925fd08819084cfe4ec566cb704 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 1, 2026, 1:02 a.m.