Triple

T22689597
Position Surface form Disambiguated ID Type / Status
Subject Mercer University School of Law E561013 entity
Predicate namedAfter P63 FINISHED
Object Walter F. George 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: Walter F. George | Statement: [Mercer University School of Law, namedAfter, Walter F. George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Walter F. George
Context triple: [Mercer University School of Law, namedAfter, Walter F. George]
  • A. Walter F. George chosen
    Walter F. George was a long-serving Democratic U.S. Senator from Georgia known for his influential roles in foreign policy and finance during the mid-20th century.
  • B. Lawrence A. Maddox
    Lawrence A. Maddox is a film editor best known for his work on genre films such as the horror-western From Dusk Till Dawn 3: The Hangman's Daughter.
  • C. Ray Dandridge
    Ray Dandridge was a Hall of Fame third baseman renowned as one of the greatest defensive infielders in Negro Leagues history.
  • D. Barry Loudermilk
    Barry Loudermilk is a Republican politician serving as a U.S. Representative from Georgia.
  • E. Arthur Talmadge
    Arthur Talmadge was an American record executive and music industry figure best known for co-founding the influential label Mercury Records.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1789931148190925ce9038c16413b completed April 29, 2026, 3:18 a.m.
Created at: April 17, 2026, 3:13 p.m.