Triple

T10963525
Position Surface form Disambiguated ID Type / Status
Subject Luke Bryan E259037 entity
Predicate birthName P65 FINISHED
Object Thomas Luther Bryan E259037 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: Thomas Luther Bryan | Statement: [Luke Bryan, birthName, Thomas Luther Bryan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Luther Bryan
Context triple: [Luke Bryan, birthName, Thomas Luther Bryan]
  • A. Thomas Luther Bryan chosen
    Thomas Luther Bryan is the birth name of Luke Bryan, a popular American country music singer and songwriter known for numerous chart-topping hits.
  • B. Clark W. Bryan
    Clark W. Bryan was an American publisher best known for creating the influential women's magazine Good Housekeeping in the late 19th century.
  • C. David Chester Gibbons
    David Chester Gibbons is a British comic book artist and writer best known for co-creating and illustrating the acclaimed graphic novel "Watchmen."
  • D. John Marshall Clemens
    John Marshall Clemens was an American lawyer, judge, and the father of author Mark Twain (Samuel Clemens).
  • E. Albert Mussey Johnson
    Albert Mussey Johnson was an early 20th-century American businessman and investor best known as the wealthy patron and co-developer of Scotty’s Castle in Death Valley, California.
  • 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_69d6aa88500c819097d7032ca578e74f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d77147f7108190a3b68ba1dd1c130e completed April 9, 2026, 9:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d77277108190979f1b1edeac8964 completed April 18, 2026, 12:59 a.m.
Created at: April 8, 2026, 9:23 p.m.