Triple
T23006412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cressida Bonas |
E572781
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Jeffrey Bonas |
—
|
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: Jeffrey Bonas | Statement: [Cressida Bonas, father, Jeffrey Bonas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeffrey Bonas Context triple: [Cressida Bonas, father, Jeffrey Bonas]
-
A.
Jeffrey Bonas
chosen
Jeffrey Bonas is a British businessman best known as the father of actress and model Cressida Bonas.
-
B.
Mark DeBonis
Mark DeBonis is a Canadian stand-up comedian and actor known for his work in independent films and on the comedy circuit.
-
C.
Jeffrey Heath
Jeffrey Heath is a linguist renowned for his extensive fieldwork and documentation of Dogon and other African languages.
-
D.
Greg Finton
Greg Finton is a film editor known for his work on documentaries and feature films, including the acclaimed documentary "He Named Me Malala."
-
E.
Brian Bickford
Brian Bickford is an individual notable enough to be specifically cited as a bearer of the surname Bickford.
- 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_69e245b6a3ac81908087599eefe3e365 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1835706dc8190b3f9743c0f336bb2 |
completed | April 29, 2026, 4:04 a.m. |
Created at: April 17, 2026, 3:51 p.m.