Triple
T18963036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bunge la Tanzania |
E463956
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | Bunge |
—
|
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: Bunge | Statement: [Bunge la Tanzania, shortName, Bunge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bunge Context triple: [Bunge la Tanzania, shortName, Bunge]
-
A.
Bunge
chosen
Bunge is the unicameral legislative body and main law-making institution of the United Republic of Tanzania.
-
B.
Bunge
Bunge is a surname most notably associated with Nikolai Bunge, a prominent 19th-century Russian economist and statesman.
-
C.
Cargill
Cargill is a large American privately held global food and agribusiness company involved in commodities trading, food production, and agricultural services.
-
D.
Archer Daniels Midland
Archer Daniels Midland is a large American multinational food processing and commodities trading corporation.
-
E.
Bunge Land
Bunge Land is a low-lying, largely sandy Arctic island or landmass within Russia’s New Siberian Islands archipelago, known for being periodically flooded by the sea.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d5d420f481909aa22a0d22ac4af1 |
completed | April 20, 2026, 7:29 a.m. |
Created at: April 10, 2026, noon