Triple
T17966629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harbor Springs |
E449224
|
entity |
| Predicate | hasNearbyCity |
P350
|
FINISHED |
| Object | Charlevoix |
—
|
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: Charlevoix | Statement: [Harbor Springs, hasNearbyCity, Charlevoix]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charlevoix Context triple: [Harbor Springs, hasNearbyCity, Charlevoix]
-
A.
Charlevoix
Charlevoix is a scenic region of Quebec known for its mountainous landscapes, St. Lawrence River shoreline, and popular outdoor tourism.
-
B.
Charlevoix
chosen
Charlevoix is a small resort city and popular tourist destination on the shores of Lake Michigan in northern Michigan, known for its waterfront, historic architecture, and outdoor recreation.
-
C.
Valcartier
Valcartier is a locality in Quebec, Canada, best known for its large Canadian Forces military base and nearby recreational facilities.
-
D.
Langelier
Langelier is a Montreal Metro station in the Mercier–Hochelaga-Maisonneuve borough, serving the Green Line of the city’s rapid transit system.
-
E.
Langelier
Langelier was a federal electoral district in Quebec, Canada, represented in the House of Commons during the 20th century.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b1380960819089a3c0dd7cd57e5e |
completed | April 19, 2026, 10:40 a.m. |
Created at: April 10, 2026, 10:22 a.m.