Triple
T10131010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lower Peninsula of Michigan |
E226336
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object | Lansing |
E16556
|
NE FINISHED |
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: Lansing | Statement: [Lower Peninsula of Michigan, hasMajorCity, Lansing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lansing Context triple: [Lower Peninsula of Michigan, hasMajorCity, Lansing]
-
A.
Lansing
Lansing is a surname of English origin borne by various notable individuals, including American statesman Robert Lansing.
-
B.
Lansing
Lansing is a small village located within Tompkins County in central New York State, near the city of Ithaca.
-
C.
Lansing, Michigan
chosen
Lansing, Michigan is the capital city of the U.S. state of Michigan and a historic center of automobile manufacturing and industry.
-
D.
Kalamazoo
Kalamazoo is a mid-sized city in southwestern Michigan known for its historic downtown, educational institutions like Western Michigan University, and a legacy of manufacturing and craft beer.
-
E.
Saginaw
Saginaw is a residential suburb located within the greater Dallas urban area.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca843057b48190a86730167f5d6b98 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd33557a88190b5fb1938646d8532 |
completed | April 2, 2026, 2:23 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d65296ee98819096de701e3b945001 |
completed | April 8, 2026, 1:05 p.m. |
Created at: March 30, 2026, 9:06 p.m.