Triple

T6278702
Position Surface form Disambiguated ID Type / Status
Subject Sapphire E140725 entity
Predicate familyName P18 FINISHED
Object Lofton E436636 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: Lofton | Statement: [Sapphire, familyName, Lofton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lofton
Context triple: [Sapphire, familyName, Lofton]
  • A. Lofton chosen
    Lofton is a masculine given name, most notably borne by Lofton R. Henderson, a U.S. Navy aviator killed at the Battle of Midway in World War II.
  • B. Thomasville
    Thomasville is a small city in southern Georgia known for its historic downtown, Victorian architecture, and annual Rose Show and Festival.
  • C. Glennville
    Glennville is a small city in southeastern Georgia, United States, known for its agricultural surroundings and rural community character.
  • D. Nashborough
    Nashborough was an early American frontier settlement that later became the city of Nashville, Tennessee.
  • E. Maynardville
    Maynardville is a small city in Union County, Tennessee, known as the county seat and part of the greater Knoxville metropolitan region.
  • 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_69c008cc158881908df6ec94a911c736 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c063dc55d48190b5ed48a50f3a742e completed March 22, 2026, 9:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69c519549cf0819096d01c23f6c915eb completed March 26, 2026, 11:32 a.m.
Created at: March 22, 2026, 4:26 p.m.