Triple

T12270841
Position Surface form Disambiguated ID Type / Status
Subject Kenneth Prewitt E292465 entity
Predicate name P16 FINISHED
Object Kenneth Prewitt E292465 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: Kenneth Prewitt | Statement: [Kenneth Prewitt, name, Kenneth Prewitt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kenneth Prewitt
Context triple: [Kenneth Prewitt, name, Kenneth Prewitt]
  • A. Kenneth Prewitt chosen
    Kenneth Prewitt is an American political scientist and former director of the U.S. Census Bureau who oversaw the 2000 United States census.
  • B. William K. Reilly
    William K. Reilly is an American environmental leader and former Administrator of the U.S. Environmental Protection Agency known for his influential role in advancing environmental policy and conservation.
  • C. Donald E. Stokes
    Donald E. Stokes was an influential American political scientist known for his pioneering work in electoral behavior and public opinion research.
  • D. Donald A. Henderson
    Donald A. Henderson was an American epidemiologist who led the World Health Organization’s successful global campaign to eradicate smallpox.
  • E. John E. Tourtellotte
    John E. Tourtellotte was an American architect best known for his influential early 20th-century public and commercial buildings in Idaho and the broader Pacific Northwest.
  • 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_69d6ab6856488190b5d31178d5015f8e completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cdea6e881908e13f8259bad6ddc completed April 10, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e6981b48190a0fc5a571c425be1 completed May 2, 2026, 3:55 p.m.
Created at: April 8, 2026, 9:52 p.m.