Triple

T6428213
Position Surface form Disambiguated ID Type / Status
Subject Wendell Willkie E128111 entity
Predicate residence P75 FINISHED
Object Akron, Ohio E27222 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: Akron, Ohio | Statement: [Wendell Willkie, residence, Akron, Ohio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akron, Ohio
Context triple: [Wendell Willkie, residence, Akron, Ohio]
  • A. Akron chosen
    Akron is an industrial city in northeastern Ohio known historically for its rubber and tire manufacturing industry.
  • B. Hamilton, Ohio
    Hamilton, Ohio is a historic industrial city in southwestern Ohio that serves as the county seat of Butler County and is part of the greater Cincinnati–Miami Valley region.
  • C. Cleveland
    Cleveland is a small city in northeastern Georgia known as a gateway to the Appalachian Mountains and nearby gold-mining and outdoor recreation areas.
  • D. Cleveland
    Cleveland is a major city in the U.S. state of Ohio, known for its industrial history, cultural institutions like the Rock and Roll Hall of Fame, and its location on the southern shore of Lake Erie.
  • E. Cleveland
    Cleveland is a common English surname most prominently associated with Grover Cleveland, the 22nd and 24th president of the United States.
  • 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_69c00838de888190af2eec0b80495efa completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c06922a27881908c5571f2aa31e0c1 completed March 22, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69ca73246e9c819099fe003f1274523e completed March 30, 2026, 12:57 p.m.
Created at: March 22, 2026, 4:44 p.m.