Triple
T22548237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Distell Group |
E557486
|
entity |
| Predicate | owns |
P347
|
FINISHED |
| Object | Amarula |
—
|
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: Amarula | Statement: [Distell Group, owns, Amarula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amarula Context triple: [Distell Group, owns, Amarula]
-
A.
Amarula
chosen
Amarula is a South African cream liqueur made from the fermented fruit of the marula tree, known for its smooth, caramel-like flavor and association with African wildlife.
-
B.
Mirinda
Mirinda is a fruit-flavored carbonated soft drink brand owned and produced by PepsiCo, popular in many countries around the world.
-
C.
Leite
Leite is a Portuguese-language surname commonly found in Brazil and other Lusophone countries.
-
D.
Kola
Kola is a small town in Russia’s Murmansk Oblast, located near the city of Murmansk on the Kola Peninsula in the far northwest of the country.
-
E.
Kola
Kola is a historical settlement located in the medieval Georgian region of Tao-Klarjeti, known for its role in the early Christian and political history of the area.
- 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f372df48190ae5dd461b1230bc7 |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:52 p.m.