Triple

T21861415
Position Surface form Disambiguated ID Type / Status
Subject Loews Chicago Hotel E539770 entity
Predicate near P350 FINISHED
Object Lake Michigan 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: Lake Michigan | Statement: [Loews Chicago Hotel, near, Lake Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lake Michigan
Context triple: [Loews Chicago Hotel, near, Lake Michigan]
  • A. Lake Michigan chosen
    Lake Michigan is one of North America’s five Great Lakes, a large freshwater lake bordered by the U.S. states of Illinois, Indiana, Michigan, and Wisconsin.
  • B. Lake, Michigan
    Lake, Michigan is an unincorporated community in Clare County known for its small-town character and proximity to lakes and outdoor recreation in central Michigan.
  • C. Lake Huron
    Lake Huron is one of North America's five Great Lakes, known for its vast size, clear waters, and extensive shoreline dotted with islands, including Manitoulin Island, the world's largest freshwater island.
  • D. El Huron
    El Huron is a minor criminal character in the action film "Crank: High Voltage."
  • E. Lake Michigamme
    Lake Michigamme is a large, scenic freshwater lake in Michigan’s Upper Peninsula known for its recreational opportunities such as fishing, boating, and camping.
  • 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_69e0c47829648190bbe2d1d7033768ec completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0d63ae3708190b7ee04c1487713c9 completed April 28, 2026, 3:46 p.m.
Created at: April 16, 2026, 6:56 p.m.