Triple

T18475483
Position Surface form Disambiguated ID Type / Status
Subject Franklin, Tennessee E451419 entity
Predicate hasHistoricSite P1098 FINISHED
Object Carnton 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: Carnton | Statement: [Franklin, Tennessee, hasHistoricSite, Carnton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carnton
Context triple: [Franklin, Tennessee, hasHistoricSite, Carnton]
  • A. Carnton chosen
    Carnton is a historic plantation house and Civil War site in Franklin, Tennessee, best known for its role as a field hospital and burial ground after the Battle of Franklin.
  • B. Cresson
    Cresson is a French surname most notably borne by Édith Cresson, who served as France’s first female prime minister.
  • C. Tilghman
    Tilghman is a surname most notably associated with Shirley M. Tilghman, a prominent molecular biologist and former president of Princeton University.
  • D. Tilghman
    Tilghman is a masculine given name of English origin that has been borne by various notable American figures, including politicians and military officers.
  • E. Brigden
    Brigden is a small rural community located within St. Clair Township in southwestern Ontario, Canada.
  • 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_69d8d38465a0819099b9b42d2a662ac1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53062f67881909620c4e8fc00eb7d completed April 19, 2026, 7:43 p.m.
Created at: April 10, 2026, 11:34 a.m.