Triple
T20903152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gratiot County, Michigan |
E514722
|
entity |
| Predicate | postalAbbreviation |
P43
|
FINISHED |
| Object | MI |
—
|
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: MI | Statement: [Gratiot County, Michigan, postalAbbreviation, MI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MI Context triple: [Gratiot County, Michigan, postalAbbreviation, MI]
-
A.
MI
chosen
MI is the official two-letter United States Postal Service abbreviation for the state of Michigan.
-
B.
MI
MI is the commonly used abbreviation for the Mumbai Indians, a prominent franchise cricket team in the Indian Premier League.
-
C.
MI
MI is the vehicle registration code used on license plates for vehicles registered in Minden, a town in Germany.
-
D.
MI
MI is the Mathematical Institute of Leiden University, a department focused on research and education in mathematics.
-
E.
MI
MI is the Microscopic Imager, a close-up camera instrument on the Mars Exploration Rover used to capture detailed images of Martian rocks and soil.
- 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_69e0b4f8a1108190bce3d31331290ced |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e8fd7e4481909088b7f74ba24549 |
completed | April 21, 2026, 3:03 a.m. |
Created at: April 16, 2026, 12:47 p.m.