Triple
T22918622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mirinda |
E568796
|
entity |
| Predicate | competesWith |
P1375
|
FINISHED |
| Object | Fanta |
—
|
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: Fanta | Statement: [Mirinda, competesWith, Fanta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fanta Context triple: [Mirinda, competesWith, Fanta]
-
A.
Fanta
chosen
Fanta is a globally popular fruit-flavored soft drink brand known for its bright colors and wide variety of flavors.
-
B.
Koka Kola
Koka Kola is a punk rock song by The Clash from their landmark 1979 album "London Calling," known for its satirical take on consumerism and corporate culture.
-
C.
P-Cola
P-Cola is a common shorthand nickname for the city of Pensacola in the Florida Panhandle.
-
D.
Chero-Cola
Chero-Cola was the early 20th-century soft drink brand that later evolved into the better-known RC Cola.
-
E.
Sunkist soda
Sunkist soda is a popular orange-flavored soft drink brand known for its bright citrus taste and wide distribution in the United States.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1807b254c8190bb84596dcacaa35e |
completed | April 29, 2026, 3:52 a.m. |
Created at: April 17, 2026, 3:42 p.m.