Triple

T5283678
Position Surface form Disambiguated ID Type / Status
Subject Kelly Field E119558 entity
Predicate city P40 FINISHED
Object Corvallis E2907 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: Corvallis | Statement: [Kelly Field, city, Corvallis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Corvallis
Context triple: [Kelly Field, city, Corvallis]
  • A. Corvallis, Oregon chosen
    Corvallis, Oregon is a small city in western Oregon known as a college town, serving as the home of Oregon State University and a hub for education, research, and outdoor recreation.
  • B. Newport, Oregon
    Newport, Oregon is a coastal city on the central Oregon coast known for its working waterfront, marine research institutions, and popular attractions like the Oregon Coast Aquarium.
  • C. Salem, Oregon
    Salem, Oregon is the capital city of the U.S. state of Oregon, known as a regional center for government, education, and agriculture in the Willamette Valley.
  • D. Aumsville, Oregon
    Aumsville, Oregon is a small city in the Willamette Valley region of western Oregon, located southeast of Salem.
  • E. Eugene, Oregon
    Eugene, Oregon is a mid-sized city in western Oregon known for its vibrant arts scene, outdoor recreation, and the University of Oregon.
  • 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_69bd446d05a8819092ad333a3f9c8d5c completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd84c8d2bc8190840699e5a526b756 completed March 20, 2026, 5:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf10dc64f4819091fcbc39c0e3034b completed March 21, 2026, 9:42 p.m.
Created at: March 20, 2026, 1:52 p.m.