Triple
T18700562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Berube |
E457237
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Berube |
—
|
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: Berube | Statement: [Craig Berube, familyName, Berube]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berube Context triple: [Craig Berube, familyName, Berube]
-
A.
Berube
chosen
Berube is a surname most notably associated with Craig Berube, a former NHL player and Stanley Cup–winning head coach.
-
B.
Reaume
Reaume is a surname of likely French origin borne by individuals such as Helen Emma Reaume.
-
C.
Andre LeBlanc
Andre LeBlanc is known primarily as the brother of American actor Christian LeBlanc, who plays Michael Baldwin on the soap opera "The Young and the Restless."
-
D.
Robert-Fleury
Robert-Fleury is the surname of a notable French artistic family that includes the 19th-century painter and teacher Tony Robert-Fleury.
-
E.
Ian Laperrière
Ian Laperrière is a retired Canadian professional ice hockey right winger who played over 1,000 NHL games, primarily known for his gritty, hard-working style and leadership.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e562eb06b481908ef9efdb976008f3 |
completed | April 19, 2026, 11:19 p.m. |
Created at: April 10, 2026, 11:49 a.m.