Triple
T19305520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Embrun |
E482816
|
entity |
| Predicate | nearbyCommunity |
P4647
|
FINISHED |
| Object | Casselman |
—
|
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: Casselman | Statement: [Embrun, nearbyCommunity, Casselman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Casselman Context triple: [Embrun, nearbyCommunity, Casselman]
-
A.
Casselman
chosen
Casselman is a small bilingual village and municipality in Eastern Ontario, Canada, known for its francophone community and location along the South Nation River.
-
B.
Luske
Luske is a surname most notably associated with Hamilton Luske, an American animator and film director for Walt Disney Studios.
-
C.
Mackey
Mackey is a surname most prominently associated with John Mackey, the co-founder and longtime CEO of Whole Foods Market.
-
D.
Hassler
Hassler Whitney was an influential American mathematician known for his foundational work in differential topology and manifold theory.
-
E.
Laird
Laird is a given name of Scottish origin traditionally used as a masculine middle or first name, associated with landownership and nobility.
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e604c84fe08190869463bdd0324160 |
completed | April 20, 2026, 10:49 a.m. |
Created at: April 10, 2026, 1:31 p.m.