Triple

T19688748
Position Surface form Disambiguated ID Type / Status
Subject Western Illinois E472778 entity
Predicate hasCollegeTown P27837 FINISHED
Object Macomb, Illinois 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: Macomb, Illinois | Statement: [Western Illinois, hasCollegeTown, Macomb, Illinois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Macomb, Illinois
Context triple: [Western Illinois, hasCollegeTown, Macomb, Illinois]
  • A. Macomb, Illinois chosen
    Macomb, Illinois is a small Midwestern city in the United States best known as the home of Western Illinois University.
  • B. Montgomery, Illinois
    Montgomery, Illinois is a suburban village in the Chicago metropolitan area spanning Kane and Kendall counties along the Fox River.
  • C. Sycamore, Illinois
    Sycamore, Illinois is a small historic city in northern Illinois known for its preserved downtown district and annual Sycamore Pumpkin Festival.
  • D. Midlothian, Illinois
    Midlothian, Illinois is a suburban village in Cook County, part of the Chicago metropolitan area, known for its residential neighborhoods and commuter access to the city.
  • E. Valmeyer, Illinois
    Valmeyer, Illinois is a small village in Monroe County best known for relocating to higher ground after the devastating Great Flood of 1993.
  • 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_69d8e515bef88190bc30781aea50537a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6420e5b788190a63ff6b83383b0e8 completed April 20, 2026, 3:11 p.m.
Created at: April 10, 2026, 1:45 p.m.