Triple
T22893046
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Janet Banana |
E568092
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Canaan Banana |
—
|
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: Canaan Banana | Statement: [Janet Banana, spouse, Canaan Banana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Canaan Banana Context triple: [Janet Banana, spouse, Canaan Banana]
-
A.
Canaan Banana
chosen
Canaan Banana was a Zimbabwean Methodist minister, theologian, and politician who became the country’s first president after independence in 1980.
-
B.
Banana North
Banana North is a rural locality within Queensland’s Banana Shire, known primarily for its agricultural landscape and small population.
-
C.
Bannans
Bannans is a small commune in the Doubs department of eastern France, situated in the Bourgogne-Franche-Comté region.
-
D.
Banana East
Banana East is a rural locality within Queensland’s Banana Shire, known primarily for its agricultural landscape and small population.
-
E.
Banana South
Banana South is a rural locality within Queensland’s Banana Shire, known primarily for its agricultural landscape and small-community character.
- 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_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f17fc66dbc81909b31c068d7f2c531 |
completed | April 29, 2026, 3:49 a.m. |
Created at: April 17, 2026, 3:40 p.m.