Triple
T12698424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angolagate arms trafficking affair |
E303395
|
entity |
| Predicate | armsSupplierCountry |
P89764
|
FINISHED |
| Object | Eastern European countries |
—
|
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: Eastern European countries | Statement: [Angolagate arms trafficking affair, armsSupplierCountry, Eastern European countries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armsSupplierCountry Context triple: [Angolagate arms trafficking affair, armsSupplierCountry, Eastern European countries]
-
A.
assemblyCountry
Indicates the country in which an item, product, or component is assembled.
-
B.
armamentOrigin
chosen
Indicates the source or place from which a weapon or armament originates or is supplied.
-
C.
aircraftOriginCountry
Indicates the country from which an aircraft originates, such as where it was built, registered, or primarily associated.
-
D.
countryOfOrigin
Indicates the country from which an entity originally comes or was first produced, created, or established.
-
E.
armsTrade
Indicates the buying, selling, or exchange of weapons or military equipment between parties.
- 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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d962a32c6481908ddaddae4ea267bf |
completed | April 10, 2026, 8:50 p.m. |
| PD | Predicate disambiguation | batch_69d960be63f081908a5ef5ef17a311bf |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:22 p.m.