Triple
T7677780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DeVos Art Museum |
E173908
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Marquette |
E5180
|
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: Marquette | Statement: [DeVos Art Museum, city, Marquette]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marquette Context triple: [DeVos Art Museum, city, Marquette]
-
A.
Marquette
chosen
Marquette is a city in Michigan’s Upper Peninsula known as a key shipping and commercial hub on the southern shore of Lake Superior.
-
B.
Marquette
Marquette is a French surname most notably associated with the 17th-century Jesuit missionary and explorer Jacques Marquette, after whom various places and institutions in North America are named.
-
C.
Marquette, Michigan
Marquette, Michigan is a city on the southern shore of Lake Superior known as a regional hub for education, healthcare, and outdoor recreation in Michigan’s Upper Peninsula.
-
D.
Northwestern Mari
Northwestern Mari is a regional dialect of the Uralic Mari language spoken by the Mari people in parts of Russia.
-
E.
Gustavus
Gustavus is a Latinized masculine given name historically borne by several Swedish kings and used in various European and English-speaking contexts.
- 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_69c6995703e0819081de77361b602e78 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c701fd18d88190888144a7d0f228d9 |
completed | March 27, 2026, 10:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8b4fa4f9c8190a1cd2c1aa173296d |
completed | March 29, 2026, 5:13 a.m. |
Created at: March 27, 2026, 4:01 p.m.