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.