Triple

T2182291
Position Surface form Disambiguated ID Type / Status
Subject William L. Cabell E49070 entity
Predicate relative P37 FINISHED
Object Earle Cabell E2917 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: Earle Cabell | Statement: [William L. Cabell, relative, Earle Cabell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Earle Cabell
Context triple: [William L. Cabell, relative, Earle Cabell]
  • A. Earle Cabell chosen
    Earle Cabell was an American politician and businessman who served as mayor of Dallas, Texas, during the early 1960s, including at the time of President John F. Kennedy’s assassination.
  • B. Ben E. Cabell
    Ben E. Cabell was an American politician who served as mayor of Dallas, Texas, in the early 20th century.
  • C. Earle Kingston
    Earle Kingston is the husband of acclaimed Chinese American author Maxine Hong Kingston.
  • D. Earl Roberts
    Earl Roberts is a British noble title created in honor of Lord Roberts, a distinguished military leader of the late 19th and early 20th centuries.
  • E. David Cobb
    David Cobb is an American attorney and political activist best known as the Green Party’s presidential nominee in the 2004 U.S. election.
  • 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_69a88aa72d348190a9544bb5b8a4e71d completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbf0d551881909d7f907378e1b2b7 completed March 7, 2026, 6 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5da786e48190896cae8fdcee3d83 completed March 9, 2026, 5:41 a.m.
Created at: March 4, 2026, 7:45 p.m.