Triple

T19482772
Position Surface form Disambiguated ID Type / Status
Subject Cours Lafayette E487432 entity
Predicate namedAfter P63 FINISHED
Object Lafayette 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: Lafayette | Statement: [Cours Lafayette, namedAfter, Lafayette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lafayette
Context triple: [Cours Lafayette, namedAfter, Lafayette]
  • A. Lafayette
    Lafayette is a mid-sized city in southern Louisiana known as a cultural hub of Cajun and Creole music, food, and festivals.
  • B. Lafayette chosen
    Lafayette was a French aristocrat and military officer who became a key general in the American Revolutionary War and a symbol of Franco-American alliance.
  • C. Lafayette
    Lafayette is a mid-sized city in northwestern Indiana known for its proximity to Purdue University and its role as a regional economic and cultural center.
  • D. Lafayette
    Lafayette is a small city in Boulder County, Colorado, known for its family-friendly neighborhoods, parks, and proximity to the Denver–Boulder metropolitan area.
  • E. Place Lafayette
    Place Lafayette is a central public square in the town of Villeneuve-sur-Lot in southwestern France, known as a local gathering spot and focal point of urban life.
  • 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_69d8e8d924388190b847cb15bb3d0aff completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6343ab16481909b508ba0a08ea191 completed April 20, 2026, 2:12 p.m.
Created at: April 10, 2026, 1:39 p.m.