Triple

T19437521
Position Surface form Disambiguated ID Type / Status
Subject Garrett Walker E486260 entity
Predicate hasAdvisor P25349 FINISHED
Object Raymond Tusk NE NERFINISHED

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: Raymond Tusk | Statement: [Garrett Walker, hasAdvisor, Raymond Tusk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Raymond Tusk
Context triple: [Garrett Walker, hasAdvisor, Raymond Tusk]
  • A. Raymond Tusk chosen
    Raymond Tusk is a powerful billionaire industrialist and political kingmaker in the series "House of Cards," known for his behind-the-scenes influence and strategic rivalry with Frank Underwood.
  • B. Charles Boustany
    Charles Boustany is an American politician and former Republican U.S. Representative from Louisiana.
  • C. Charles Ewing
    Charles Ewing was a 19th-century American lawyer, Union Army general in the Civil War, and later a federal official, known as a prominent member of the influential Ewing family.
  • D. James Cresson
    James Cresson is a film producer best known for his work on the 1972 comedy-drama "Travels with My Aunt."
  • E. William Roberts
    William Roberts was an American screenwriter best known for writing the screenplay for the classic Western film "The Magnificent Seven" (1960).
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8d7ad488190a3373045029b0f3b completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633618c2881908f3d2a9cabb02289 completed April 20, 2026, 2:08 p.m.
Created at: April 10, 2026, 1:38 p.m.