Triple
T12970263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ford River Township, Michigan |
E321373
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object |
Ford River
Ford River is a waterway in Michigan’s Upper Peninsula that flows into Lake Michigan and lends its name to the surrounding Ford River Township.
|
E1035739
|
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: Ford River | Statement: [Ford River Township, Michigan, namedAfter, Ford River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ford River Context triple: [Ford River Township, Michigan, namedAfter, Ford River]
-
A.
Broad River
Broad River is a major waterway in central South Carolina that flows through the Columbia area and contributes to the Congaree River system.
-
B.
Long River
Long River is the English translation of the Chinese name for the Yangtze, Asia’s longest river and a major waterway in China.
-
C.
Union River
The Union River is a small river in Mason County, Washington, that flows into Hood Canal near the community of Belfair.
-
D.
Jackson River
The Jackson River is a major headwater stream in western Virginia that joins with the Cowpasture River to form the James River.
-
E.
Train River
The Train River is a smaller watercourse in Belgium that serves as a tributary within the Dyle River basin.
- 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: Ford River Triple: [Ford River Township, Michigan, namedAfter, Ford River]
Generated description
Ford River is a waterway in Michigan’s Upper Peninsula that flows into Lake Michigan and lends its name to the surrounding Ford River Township.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ford River Target entity description: Ford River is a waterway in Michigan’s Upper Peninsula that flows into Lake Michigan and lends its name to the surrounding Ford River Township.
-
A.
Broad River
Broad River is a major waterway in central South Carolina that flows through the Columbia area and contributes to the Congaree River system.
-
B.
Long River
Long River is the English translation of the Chinese name for the Yangtze, Asia’s longest river and a major waterway in China.
-
C.
Union River
The Union River is a small river in Mason County, Washington, that flows into Hood Canal near the community of Belfair.
-
D.
Jackson River
The Jackson River is a major headwater stream in western Virginia that joins with the Cowpasture River to form the James River.
-
E.
Train River
The Train River is a smaller watercourse in Belgium that serves as a tributary within the Dyle River basin.
- 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_69d80763bd6c819094437da5b20b01d2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e407e5081909424fc0c22483c28 |
completed | April 10, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f71f0c11f88190b0f0fa1d0ec74a8d |
completed | May 3, 2026, 10:10 a.m. |
| NEDg | Description generation | batch_69f721b1a5d88190b9075437c7ab81a5 |
completed | May 3, 2026, 10:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f72262ede4819095b3dc4c7cd63450 |
completed | May 3, 2026, 10:24 a.m. |
Created at: April 9, 2026, 8:34 p.m.