Triple
T894941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Allegan County |
E19322
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Dorr Township
Dorr Township is a civil township and primarily rural community located in Allegan County in the U.S. state of Michigan.
|
E116850
|
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: Dorr Township | Statement: [Allegan County, contains, Dorr Township]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dorr Township Context triple: [Allegan County, contains, Dorr Township]
-
A.
Ganges Township
Ganges Township is a rural civil township in Allegan County, Michigan, known for its agricultural landscape and proximity to the Lake Michigan shoreline.
-
B.
Saugatuck Township
Saugatuck Township is a small lakeside community in western Michigan known for its scenic Lake Michigan shoreline, dunes, and tourism-oriented economy.
-
C.
Salem Township
Salem Township is a local civil township located within Allegan County in the U.S. state of Michigan.
-
D.
Manlius Township
Manlius Township is a civil township located within Allegan County in the U.S. state of Michigan.
-
E.
Lawrence Township
Lawrence Township is a suburban municipality in Mercer County, New Jersey, known for its residential communities, shopping centers, and proximity to Princeton.
- 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: Dorr Township Triple: [Allegan County, contains, Dorr Township]
Generated description
Dorr Township is a civil township and primarily rural community located in Allegan County in the U.S. state of Michigan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dorr Township Target entity description: Dorr Township is a civil township and primarily rural community located in Allegan County in the U.S. state of Michigan.
-
A.
Ganges Township
Ganges Township is a rural civil township in Allegan County, Michigan, known for its agricultural landscape and proximity to the Lake Michigan shoreline.
-
B.
Saugatuck Township
Saugatuck Township is a small lakeside community in western Michigan known for its scenic Lake Michigan shoreline, dunes, and tourism-oriented economy.
-
C.
Salem Township
Salem Township is a local civil township located within Allegan County in the U.S. state of Michigan.
-
D.
Manlius Township
Manlius Township is a civil township located within Allegan County in the U.S. state of Michigan.
-
E.
Lawrence Township
Lawrence Township is a suburban municipality in Mercer County, New Jersey, known for its residential communities, shopping centers, and proximity to Princeton.
- 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_69a4939d37188190848be3d426ebc9ae |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad22b6fc819093e655c8ce1f738b |
completed | March 1, 2026, 9:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac257f3b2c819082a16c7242d89404 |
completed | March 7, 2026, 1:17 p.m. |
| NEDg | Description generation | batch_69ac25e6cc608190a717c7991936c3a5 |
completed | March 7, 2026, 1:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac264b6bc08190a18c4f61ea6eb0f4 |
completed | March 7, 2026, 1:21 p.m. |
Created at: March 1, 2026, 7:39 p.m.