Triple
T6621256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lapeer County |
E149677
|
entity |
| Predicate | seat |
P75
|
FINISHED |
| Object |
Lapeer
Lapeer is a small city in Michigan known as an administrative and commercial center for the surrounding rural region.
|
E793966
|
NE FINISHED |
How this triple was built (4 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: Lapeer | Statement: [Lapeer County, seat, Lapeer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lapeer Context triple: [Lapeer County, seat, Lapeer]
-
A.
Utica, Michigan
Utica, Michigan is a small suburban city in Macomb County known for its historic downtown and location along the Clinton River within the Metro Detroit area.
-
B.
Ypsilanti
Ypsilanti is a city in southeastern Michigan known for Eastern Michigan University and its historic downtown and automotive heritage.
-
C.
St. Joseph, Michigan
St. Joseph, Michigan is a small Lake Michigan shoreline city in southwestern Michigan known for its beaches, harbor, and historic downtown.
-
D.
Grand Blanc, Michigan
Grand Blanc, Michigan is a suburban city in southeastern Genesee County known for its residential communities, schools, and proximity to Flint.
-
E.
Fennville
Fennville is a small city in southwestern Michigan known for its agricultural surroundings, wineries, and proximity to Lake Michigan.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lapeer Triple: [Lapeer County, seat, Lapeer]
Generated description
Lapeer is a small city in Michigan known as an administrative and commercial center for the surrounding rural region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lapeer Target entity description: Lapeer is a small city in Michigan known as an administrative and commercial center for the surrounding rural region.
-
A.
Utica, Michigan
Utica, Michigan is a small suburban city in Macomb County known for its historic downtown and location along the Clinton River within the Metro Detroit area.
-
B.
Ypsilanti
Ypsilanti is a city in southeastern Michigan known for Eastern Michigan University and its historic downtown and automotive heritage.
-
C.
St. Joseph, Michigan
St. Joseph, Michigan is a small Lake Michigan shoreline city in southwestern Michigan known for its beaches, harbor, and historic downtown.
-
D.
Grand Blanc, Michigan
Grand Blanc, Michigan is a suburban city in southeastern Genesee County known for its residential communities, schools, and proximity to Flint.
-
E.
Fennville
Fennville is a small city in southwestern Michigan known for its agricultural surroundings, wineries, and proximity to Lake Michigan.
- F. None of above. chosen
Provenance (5 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_69c687ed8a9c81908bb671717cb192ef |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6af7ccaa481908b383b4fd671fa78 |
completed | March 27, 2026, 4:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0f32101e08190888a1f44c2224e1e |
completed | April 4, 2026, 11:16 a.m. |
| NEDg | Description generation | batch_69d0f46bd034819093e7157a3e1ac1fc |
completed | April 4, 2026, 11:22 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d0f5bf64548190b40e97b279db5105 |
completed | April 4, 2026, 11:27 a.m. |
Created at: March 27, 2026, 1:58 p.m.