Triple

T7444452
Position Surface form Disambiguated ID Type / Status
Subject John Adair E171837 entity
Predicate deathPlace P21 FINISHED
Object Harrodsburg, Kentucky E54876 NE FINISHED

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: Harrodsburg, Kentucky | Statement: [John Adair, deathPlace, Harrodsburg, Kentucky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harrodsburg, Kentucky
Context triple: [John Adair, deathPlace, Harrodsburg, Kentucky]
  • A. Harrodsburg, Kentucky chosen
    Harrodsburg, Kentucky is a historic small city recognized as the oldest permanent English settlement west of the Allegheny Mountains and a key community in central Kentucky.
  • B. Hardinsburg, Kentucky
    Hardinsburg, Kentucky is a small city in north-central Kentucky known as the administrative and commercial hub of Breckinridge County.
  • C. Barbourville, Kentucky
    Barbourville, Kentucky is a small city in southeastern Kentucky known as the county seat of Knox County and home to Union College.
  • D. Elizabethtown, Kentucky
    Elizabethtown, Kentucky is a small city in central Kentucky that serves as a regional hub for commerce, transportation, and services.
  • E. Versailles, Kentucky
    Versailles, Kentucky is a small historic city in Woodford County known for its surrounding horse farms, bourbon distilleries, and role in the heart of Kentucky’s Bluegrass region.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c68a65402881908f7869368eb746fb completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f36e9a588190b54b8bae181fc971 completed March 27, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83c54c5ec8190bc2adf5a19fdea1c completed March 28, 2026, 8:38 p.m.
Created at: March 27, 2026, 3:14 p.m.