Triple

T17420322
Position Surface form Disambiguated ID Type / Status
Subject Hank Booth E423593 entity
Predicate relative P37 FINISHED
Object Seeley Booth 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: Seeley Booth | Statement: [Hank Booth, relative, Seeley Booth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seeley Booth
Context triple: [Hank Booth, relative, Seeley Booth]
  • A. Seeley Booth chosen
    Seeley Booth is a charismatic FBI Special Agent and former Army sniper who partners with forensic anthropologist Temperance "Bones" Brennan to solve crimes in the TV series "Bones."
  • B. May Reilly Parker
    May Reilly Parker is a central supporting character in Marvel Comics best known as Peter Parker’s loving and morally grounded aunt who helps shape Spider-Man’s values.
  • C. Emily Prentiss
    Emily Prentiss is a seasoned FBI profiler known for her intelligence, resilience, and complex backstory on the crime drama series "Criminal Minds."
  • D. Mattiwilda Dobbs
    Mattiwilda Dobbs was a pioneering American coloratura soprano who became one of the first Black singers to achieve international acclaim in the world of opera.
  • E. Jordan Baxter
    Jordan Baxter is a fictional character portrayed by actor Graham Phillips, best known from his work in film and television.
  • 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44236419c8190a106748bca6f30cd completed April 19, 2026, 2:47 a.m.
Created at: April 10, 2026, 5:46 a.m.