Triple

T6025475
Position Surface form Disambiguated ID Type / Status
Subject Salem E134166 entity
Predicate airport P1065 FINISHED
Object Salem Airport E153967 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: Salem Airport | Statement: [Salem, airport, Salem Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salem Airport
Context triple: [Salem, airport, Salem Airport]
  • A. Salem Municipal Airport chosen
    Salem Municipal Airport is a public airport that provides air transportation services to the city of Salem and the surrounding Willamette Valley region in Oregon.
  • B. Willard Airport
    Willard Airport is a public airport near Champaign, Illinois, that primarily serves the Champaign–Urbana area and the University of Illinois community with regional commercial flights.
  • C. Wilson Airport
    Wilson Airport is a busy domestic and regional airport in Nairobi, Kenya, serving general aviation, charter flights, and short-haul passenger services.
  • D. Mather Airport
    Mather Airport is a public airport in Sacramento County, California, primarily serving cargo, general aviation, and military operations on the site of the former Mather Air Force Base.
  • E. Hawthorne Municipal Airport
    Hawthorne Municipal Airport is a public airport in Hawthorne, California, serving general aviation and corporate traffic in the Los Angeles metropolitan area.
  • 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_69c008742a5c8190b9cb9c2787a3d8b3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04fc08c5c819085afab5b18bce4d1 completed March 22, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11375b4448190ad3087b21ac67329 completed March 23, 2026, 10:18 a.m.
Created at: March 22, 2026, 4:07 p.m.