Triple
T8873025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michigan |
E211206
|
entity |
| Predicate | ISOCode |
P208
|
FINISHED |
| Object |
US-MI
US-MI is the ISO 3166-2 code representing the U.S. state of Michigan, known for its Great Lakes shoreline and automotive industry centered in Detroit.
|
E211207
|
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: US-MI | Statement: [Michigan, ISOCode, US-MI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: US-MI Context triple: [Michigan, ISOCode, US-MI]
-
A.
US-ME
US-ME is the ISO 3166-2 code representing the U.S. state of Maine.
-
B.
US-MT
US-MT is the ISO 3166-2 subdivision code that uniquely identifies the U.S. state of Montana.
-
C.
US-MS
US-MS is the ISO 3166-2 code representing the U.S. state of Mississippi.
-
D.
Michigan (most of state)
Michigan (most of state) is the larger portion of the Midwestern U.S. state of Michigan, encompassing its Lower Peninsula and parts of the Upper Peninsula, including major cities like Detroit, Grand Rapids, and Lansing.
-
E.
Michigan
Michigan is a U.S. state in the Great Lakes region known for its extensive freshwater coastline, automotive industry centered in Detroit, and diverse natural landscapes.
- 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: US-MI Triple: [Michigan, ISOCode, US-MI]
Generated description
US-MI is the ISO 3166-2 code representing the U.S. state of Michigan, known for its Great Lakes shoreline and automotive industry centered in Detroit.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: US-MI Target entity description: US-MI is the ISO 3166-2 code representing the U.S. state of Michigan, known for its Great Lakes shoreline and automotive industry centered in Detroit.
-
A.
US-ME
US-ME is the ISO 3166-2 code representing the U.S. state of Maine.
-
B.
US-MT
US-MT is the ISO 3166-2 subdivision code that uniquely identifies the U.S. state of Montana.
-
C.
US-MS
US-MS is the ISO 3166-2 code representing the U.S. state of Mississippi.
-
D.
Michigan (most of state)
Michigan (most of state) is the larger portion of the Midwestern U.S. state of Michigan, encompassing its Lower Peninsula and parts of the Upper Peninsula, including major cities like Detroit, Grand Rapids, and Lansing.
-
E.
Michigan
chosen
Michigan is a U.S. state in the Great Lakes region known for its extensive freshwater coastline, automotive industry centered in Detroit, and diverse natural landscapes.
- F. None of above.
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_69ca838e78748190934d82db3104f855 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc612952348190856d6964122c3f01 |
completed | April 1, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfab9e87cc8190ae3c8c683aa0921e |
completed | April 3, 2026, 11:59 a.m. |
| NEDg | Description generation | batch_69cfad35141081908033585378bf0a25 |
completed | April 3, 2026, 12:06 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfadb323988190960dd933f752c456 |
completed | April 3, 2026, 12:08 p.m. |
Created at: March 30, 2026, 6:52 p.m.