Triple
T4201170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maynardville |
E86067
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Norris Lake |
E315892
|
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: Norris Lake | Statement: [Maynardville, locatedNear, Norris Lake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norris Lake Context triple: [Maynardville, locatedNear, Norris Lake]
-
A.
Norris Lake
chosen
Norris Lake is a large, popular reservoir in eastern Tennessee known for boating, fishing, and scenic recreation along its extensive shoreline.
-
B.
Riffe Lake
Riffe Lake is a large reservoir on the Cowlitz River in southwestern Washington, popular for fishing, boating, and camping.
-
C.
Fisher Lake
Fisher Lake is a natural lake located within George Wyth State Park in Iowa, known for outdoor recreation such as fishing and boating.
-
D.
Wood Lake
Wood Lake is a freshwater lake in British Columbia’s Okanagan region, known for recreation, fishing, and its role in the local valley ecosystem.
-
E.
Fairview Lake
Fairview Lake is a small recreational and residential lake located in the city of Fairview in Multnomah County, Oregon.
- 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_69aed93b89f48190a31f6d57c760e42f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af037da30481908106b27a88d59140 |
completed | March 9, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ca6d6a17b4819089eafc70ecc1f786 |
completed | March 30, 2026, 12:32 p.m. |
Created at: March 9, 2026, 3:49 p.m.