Triple

T22285049
Position Surface form Disambiguated ID Type / Status
Subject Arnold Palmer Regional Airport E550837 entity
Predicate servesCity P82 FINISHED
Object Latrobe 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: Latrobe | Statement: [Arnold Palmer Regional Airport, servesCity, Latrobe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Latrobe
Context triple: [Arnold Palmer Regional Airport, servesCity, Latrobe]
  • A. Latrobe chosen
    Latrobe is a small city in Westmoreland County, Pennsylvania, known as the hometown of golfer Arnold Palmer and the birthplace of the banana split.
  • B. Latrobe
    Latrobe is a town in northern Tasmania, Australia, known for its historic streetscapes and proximity to the Mersey River.
  • C. Latrobe
    Latrobe is a surname most notably associated with Benjamin Henry Latrobe, a pioneering British-American architect often called the “father of American architecture.”
  • D. Monongahela, Pennsylvania
    Monongahela, Pennsylvania is a small city along the Monongahela River in southwestern Pennsylvania known for its historic downtown and riverfront community.
  • E. Duquesne
    Duquesne is a French noble family name historically associated with military and colonial leadership, notably in 18th-century New France.
  • 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_69e11e44d538819097c6b8f333af3352 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15606948c81909ebaa5ea106d2b7a completed April 29, 2026, 12:51 a.m.
Created at: April 16, 2026, 8:40 p.m.