Triple

T19253253
Position Surface form Disambiguated ID Type / Status
Subject Saluki (Amtrak) E481447 entity
Predicate stopsAt P6657 FINISHED
Object Mattoon, 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: Mattoon, Illinois | Statement: [Saluki (Amtrak), stopsAt, Mattoon, Illinois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mattoon, Illinois
Context triple: [Saluki (Amtrak), stopsAt, Mattoon, Illinois]
  • A. Mattoon, Illinois chosen
    Mattoon, Illinois is a small city in east-central Illinois known historically as a regional railroad hub and for its agricultural and manufacturing economy.
  • B. Matteson, Illinois
    Matteson, Illinois is a suburban village in the Chicago metropolitan area known for its residential communities and retail centers.
  • C. Loogootee, Illinois
    Loogootee, Illinois is a small unincorporated rural community located in Fayette County in the U.S. state of Illinois.
  • D. Somonauk, Illinois
    Somonauk, Illinois is a small village in northern Illinois known for its rural character and location spanning LaSalle and DeKalb counties.
  • E. Kewanee, Illinois
    Kewanee, Illinois is a small city in Henry County known historically for its agricultural roots and manufacturing, particularly in farm equipment and boilers.
  • 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb3339648190a87d38ce42aff016 completed April 20, 2026, 10:08 a.m.
Created at: April 10, 2026, 1:28 p.m.