Triple
T10296482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belleville, Michigan |
E241502
|
entity |
| Predicate | waterBody |
P1778
|
FINISHED |
| Object | Belleville Lake |
E598629
|
NE FINISHED |
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: Belleville Lake | Statement: [Belleville, Michigan, waterBody, Belleville Lake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Belleville Lake Context triple: [Belleville, Michigan, waterBody, Belleville Lake]
-
A.
Belleville Lake
chosen
Belleville Lake is a large man-made reservoir in Wayne County, Michigan, popular for boating, fishing, and other recreational activities.
-
B.
Guelph Lake
Guelph Lake is a man-made reservoir and popular recreational area near Guelph, Ontario, known for its beaches, camping, and outdoor events.
-
C.
Bow Lake
Bow Lake is a freshwater lake in New Hampshire that serves as one of the headwater sources feeding into the Merrimack River watershed.
-
D.
Bow Lake
Bow Lake is a scenic glacial lake in the Canadian Rockies of Alberta, known for its turquoise waters, mountain backdrop, and proximity to the Icefields Parkway.
-
E.
Waterloo Lake
Waterloo Lake is a body of water located within Waterloo Lake Regional Park, serving as a central natural and recreational feature of the area.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2ea9b3c8190b11518b259d5825c |
completed | April 7, 2026, 9:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f79d2da6b48190bdd974fa9520bc87 |
completed | May 3, 2026, 7:08 p.m. |
Created at: April 6, 2026, 11:43 a.m.