Triple

T6049022
Position Surface form Disambiguated ID Type / Status
Subject Mary Cantey Sumter E134740 entity
Predicate familyName P18 FINISHED
Object Sumter
Sumter is a surname of English origin most notably associated with several prominent American historical figures and families.
E564545 NE FINISHED

How this triple was built (4 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: Sumter | Statement: [Mary Cantey Sumter, familyName, Sumter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sumter
Context triple: [Mary Cantey Sumter, familyName, Sumter]
  • A. Sumter, South Carolina
    Sumter, South Carolina is a small city in central South Carolina known for its military presence, including hosting the headquarters of United States Army Central at nearby Shaw Air Force Base.
  • B. Palmetto
    Palmetto is a long-distance Amtrak passenger train service operating along the U.S. East Coast between New York City and Savannah, Georgia.
  • C. Sumter, Georgia
    Sumter, Georgia is a small unincorporated rural community located in Sumter County in the southwestern part of the U.S. state of Georgia.
  • D. Gibbes
    Gibbes is a surname and variant spelling of Gibbs, historically borne by several notable figures in English-speaking countries.
  • E. Beaufort
    Beaufort is a firm, raw cow’s milk Alpine cheese from France renowned for its smooth texture and complex, nutty flavor.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sumter
Triple: [Mary Cantey Sumter, familyName, Sumter]
Generated description
Sumter is a surname of English origin most notably associated with several prominent American historical figures and families.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sumter
Target entity description: Sumter is a surname of English origin most notably associated with several prominent American historical figures and families.
  • A. Sumter, South Carolina
    Sumter, South Carolina is a small city in central South Carolina known for its military presence, including hosting the headquarters of United States Army Central at nearby Shaw Air Force Base.
  • B. Palmetto
    Palmetto is a long-distance Amtrak passenger train service operating along the U.S. East Coast between New York City and Savannah, Georgia.
  • C. Sumter, Georgia
    Sumter, Georgia is a small unincorporated rural community located in Sumter County in the southwestern part of the U.S. state of Georgia.
  • D. Gibbes
    Gibbes is a surname and variant spelling of Gibbs, historically borne by several notable figures in English-speaking countries.
  • E. Beaufort
    Beaufort is a firm, raw cow’s milk Alpine cheese from France renowned for its smooth texture and complex, nutty flavor.
  • F. None of above. chosen

Provenance (5 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_69c00876a69881908088a2626d3b2666 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c056f387cc8190920b846995761aec completed March 22, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c113a65164819090883dbad3be5026 completed March 23, 2026, 10:19 a.m.
NEDg Description generation batch_69c11423d05c81909298ae598c80ccb0 completed March 23, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_69c11498f2948190bcca6b8054186e75 completed March 23, 2026, 10:23 a.m.
Created at: March 22, 2026, 4:09 p.m.