Triple
T23512368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Cannonier |
E572458
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Cannonier |
—
|
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: Cannonier | Statement: [Craig Cannonier, familyName, Cannonier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cannonier Context triple: [Craig Cannonier, familyName, Cannonier]
-
A.
Cannonier
chosen
Cannonier is a surname most notably associated with Bermudian politician Craig Cannonier, a former Premier of Bermuda.
-
B.
The Cannon
The Cannon is the ring nickname of Shannon Briggs, an American heavyweight boxer and former world champion known for his punching power and outspoken personality.
-
C.
Cannon
"Cannon" is a 1970s American television crime drama series centered on the cases of a tough, overweight private detective named Frank Cannon.
-
D.
Cannon
Cannon is a common English surname borne by various notable individuals across entertainment, sports, and public life.
-
E.
Cannon
Cannon is a historic American textile and home goods brand best known for its towels, bedding, and other household linens.
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa7f583881909e78e8fe2e6e25fe |
completed | April 29, 2026, 6:51 a.m. |
Created at: April 17, 2026, 6:07 p.m.