Triple
T18706535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Five Points, Michigan |
E457382
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Five Points, Michigan |
—
|
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: Five Points, Michigan | Statement: [Five Points, Michigan, hasName, Five Points, Michigan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Five Points, Michigan Context triple: [Five Points, Michigan, hasName, Five Points, Michigan]
-
A.
Five Points, Michigan
chosen
Five Points, Michigan is an unincorporated community located within Eaton County in the U.S. state of Michigan.
-
B.
Beacon Hill, Michigan
Beacon Hill, Michigan is a small community located within Portage Charter Township in Michigan’s Upper Peninsula.
-
C.
Eastpointe, Michigan
Eastpointe, Michigan is a suburban city in Macomb County that forms part of the northeastern Detroit metropolitan area.
-
D.
Frenchtown, Michigan
Frenchtown, Michigan is a historic community in Monroe County known for its early French settlement and role in the War of 1812.
-
E.
Lakeview, Michigan
Lakeview, Michigan is a small rural village in central Michigan known for its close-knit community and proximity to several lakes and outdoor recreation areas.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5671717b88190974f542015f641e8 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 10, 2026, 11:50 a.m.