Triple

T4302931
Position Surface form Disambiguated ID Type / Status
Subject Mary Cheney E99882 entity
Predicate notableRelative P367 FINISHED
Object Liz Cheney E92768 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: Liz Cheney | Statement: [Mary Cheney, notableRelative, Liz Cheney]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liz Cheney
Context triple: [Mary Cheney, notableRelative, Liz Cheney]
  • A. Liz Cheney chosen
    Liz Cheney is an American attorney and Republican politician who served as the U.S. Representative for Wyoming and became nationally prominent for her outspoken criticism of Donald Trump and role on the House January 6th Committee.
  • B. Harriet Hageman
    Harriet Hageman is a Republican politician and attorney from Wyoming who serves as the state's at-large U.S. Representative after defeating Liz Cheney in a high-profile 2022 primary.
  • C. Cynthia Lummis
    Cynthia Lummis is a Republican politician from Wyoming who has served as both a U.S. representative and the state's first female U.S. senator.
  • D. Kay Bailey Hutchison
    Kay Bailey Hutchison is an American attorney and Republican politician who served as a long-time U.S. Senator from Texas.
  • E. Christian Chabot
    Christian Chabot is an American entrepreneur best known as the co-founder and former CEO of the data visualization software company Tableau.
  • 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_69b345528ebc8190b5abc7e95094792d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b350b792608190ac778b79c740256a completed March 12, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5db8a3a0481909d24f214f56bd21e completed March 14, 2026, 10:04 p.m.
Created at: March 12, 2026, 11:08 p.m.