Triple

T17220193
Position Surface form Disambiguated ID Type / Status
Subject Mayes County E417957 entity
Predicate bordersCounty P6346 FINISHED
Object Craig County 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: Craig County | Statement: [Mayes County, bordersCounty, Craig County]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Craig County
Context triple: [Mayes County, bordersCounty, Craig County]
  • A. Craig County chosen
    Craig County is a county in northeastern Oklahoma, United States, known for its rural communities and location within the region often referred to as Green Country.
  • B. Marshall County
    Marshall County is a county in northern Alabama known for its scenic location around Lake Guntersville and its mix of small towns and rural communities.
  • C. Marshall County
    Marshall County is a centrally located county in the U.S. state of Iowa, known for its agricultural landscape and the city of Marshalltown as its county seat.
  • D. Marshall County
    Marshall County is a rural county in northwestern Minnesota known for its agricultural landscape and small communities.
  • E. Marshall County
    Marshall County is a county in central Tennessee known for its rural communities, agricultural economy, and county seat of Lewisburg.
  • 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42ddd52d4819098b51d55e063c8ab completed April 19, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:38 a.m.