Triple

T19388821
Position Surface form Disambiguated ID Type / Status
Subject Williamson County, Illinois E485006 entity
Predicate hasCity P316 FINISHED
Object Marion, 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: Marion, Illinois | Statement: [Williamson County, Illinois, hasCity, Marion, Illinois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion, Illinois
Context triple: [Williamson County, Illinois, hasCity, Marion, Illinois]
  • A. Marion, Illinois chosen
    Marion, Illinois is a small city in southern Illinois known as a regional hub for commerce, healthcare, and transportation in the area.
  • B. Marshall, Illinois
    Marshall, Illinois is a small city in Clark County known for its historic downtown, proximity to the Indiana border, and role as a local commercial and transportation hub.
  • C. Montgomery, Illinois
    Montgomery, Illinois is a suburban village in the Chicago metropolitan area spanning Kane and Kendall counties along the Fox River.
  • D. Roanoke, Illinois
    Roanoke, Illinois is a small village in Woodford County that forms part of the broader Peoria region in central Illinois.
  • E. Macon, Illinois
    Macon, Illinois is a small city in central Illinois known for its rural community character within Macon County.
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61b425e848190ab5ae8ae0a034fe2 completed April 20, 2026, 12:25 p.m.
Created at: April 10, 2026, 1:36 p.m.