Triple

T19751493
Position Surface form Disambiguated ID Type / Status
Subject Bobby Franks E474385 entity
Predicate father P120 FINISHED
Object Jacob Franks 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: Jacob Franks | Statement: [Bobby Franks, father, Jacob Franks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jacob Franks
Context triple: [Bobby Franks, father, Jacob Franks]
  • A. Jacob Franks chosen
    Jacob Franks was a wealthy Chicago businessman and the father of Bobby Franks, the teenage victim in the infamous 1924 Leopold and Loeb murder case.
  • B. Jonathan Owens
    Jonathan Owens is an American professional football safety in the NFL who gained additional public attention through his marriage to gymnast Simone Biles.
  • C. Dave Prater
    Dave Prater was an American soul and R&B singer best known as one half of the influential duo Sam & Dave, famed for hits like "Soul Man" and "Hold On, I'm Comin'."
  • D. Brandon Peters
    Brandon Peters is known primarily as the husband of classic Hollywood actress Miriam Hopkins.
  • E. Ryan Finley
    Ryan Finley is an American entrepreneur best known as the founder of the online survey platform SurveyMonkey.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65299a7048190a9b22307ac06bd03 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:48 p.m.