Triple

T8354997
Position Surface form Disambiguated ID Type / Status
Subject Kansas Territory E196661 entity
Predicate capital P234 FINISHED
Object Topeka E19041 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: Topeka | Statement: [Kansas Territory, capital, Topeka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Topeka
Context triple: [Kansas Territory, capital, Topeka]
  • A. Topeka, Kansas chosen
    Topeka, Kansas is the capital city of the U.S. state of Kansas, historically significant as the community at the center of the landmark school desegregation case Brown v. Board of Education.
  • B. Wichita
    Wichita is a 1955 American Western film starring Joel McCrea as lawman Wyatt Earp in the turbulent Kansas cattle town.
  • C. Wichita
    Wichita is a small unincorporated community located in Guthrie County, Iowa.
  • D. Wichita
    Wichita is a savvy, resourceful con artist and one of the central survivors in the post-apocalyptic comedy film "Zombieland."
  • E. Wichita, Kansas
    Wichita, Kansas is the largest city in the state of Kansas, known as a major center for the U.S. aircraft industry and situated in south-central Kansas along the Arkansas River.
  • 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_69ca82f08b348190bfb7881944bbff6f completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb8048edb88190a1980ad74818b898 completed March 31, 2026, 8:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce395d11748190b7568be1d43d7859 completed April 2, 2026, 9:39 a.m.
Created at: March 30, 2026, 5:59 p.m.