Triple

T18725922
Position Surface form Disambiguated ID Type / Status
Subject Jefferson Seminary E457897 entity
Predicate hasCity P316 FINISHED
Object Louisville 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: Louisville | Statement: [Jefferson Seminary, hasCity, Louisville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louisville
Context triple: [Jefferson Seminary, hasCity, Louisville]
  • A. Louisville
    Louisville is a historic town in eastern Georgia that briefly served as the state’s capital in the late 18th century.
  • B. Louisville
    Louisville is a small city in Colorado known for its high quality of life, historic downtown, and proximity to the Rocky Mountains.
  • C. Louisville, Kentucky chosen
    Louisville, Kentucky is the largest city in the state of Kentucky, known for the Kentucky Derby horse race, its historic bourbon distilleries, and its role as a major cultural and economic hub in the Ohio River Valley.
  • D. Paducah
    Paducah is a small riverfront city in western Kentucky known for its vibrant arts scene, historic downtown, and role as a regional cultural hub.
  • E. Paris, Kentucky
    Paris, Kentucky is a small historic city in Bourbon County known for its role in the heart of Kentucky’s Bluegrass horse country and its preserved 19th-century architecture.
  • 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d73f68c81908a9ddf2cc2fb9813 completed April 20, 2026, 12:04 a.m.
Created at: April 10, 2026, 11:50 a.m.