Triple

T4639833
Position Surface form Disambiguated ID Type / Status
Subject Myrlie Evers E101624 entity
Predicate familyName P18 FINISHED
Object Evers E101623 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: Evers | Statement: [Myrlie Evers, familyName, Evers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evers
Context triple: [Myrlie Evers, familyName, Evers]
  • A. Evers chosen
    Evers is the surname of Medgar Evers, the prominent American civil rights activist assassinated in 1963 for his work challenging racial segregation and discrimination.
  • B. Dirksen
    Dirksen is a surname most notably associated with Everett Dirksen, a prominent mid-20th-century American politician and U.S. Senate Minority Leader.
  • C. Harrison Kohl
    Harrison Kohl was an architect known for designing the U.S. Embassy building in Berlin.
  • D. Brian Whitmer
    Brian Whitmer is a technology entrepreneur best known as a co-founder of Instructure, the company behind the Canvas learning management system.
  • E. Maddison
    Maddison is a given name and surname, often used as a variant spelling of Madison.
  • 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_69bd43d3bc7c81908f81fcf380476b0f completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a8e0ee88190becab97d2ef1571a completed March 20, 2026, 2:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfacf3cb08190a080e5ed1063902f completed March 21, 2026, 1:56 a.m.
Created at: March 20, 2026, 1:14 p.m.