Triple
T20187798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Millennium Force |
E492906
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Sandusky |
—
|
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: Sandusky | Statement: [Millennium Force, city, Sandusky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandusky Context triple: [Millennium Force, city, Sandusky]
-
A.
Sandusky, Ohio
chosen
Sandusky, Ohio is a city on the shores of Lake Erie best known as a regional tourist hub and home to the Cedar Point amusement park.
-
B.
Sandusky, Michigan
Sandusky, Michigan is a small city in Michigan’s Thumb region that serves as the county seat of Sanilac County and a local hub for the surrounding rural area.
-
C.
Johnstown, Ohio
Johnstown, Ohio is a small village in central Ohio known for its close-knit community and location within the Columbus metropolitan area.
-
D.
Johnstown
Johnstown is a small town in northern Colorado known for its residential communities and proximity to larger Front Range cities like Loveland and Greeley.
-
E.
Johnstown
Johnstown is a small community in eastern Ontario, Canada, located along the St. Lawrence River near the Canada–U.S. border.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ad2c43c8190a2fc5ef2a0514e53 |
completed | April 20, 2026, 6:05 p.m. |
Created at: April 11, 2026, 11:37 p.m.