Triple

T20986379
Position Surface form Disambiguated ID Type / Status
Subject Raphael Semmes E516900 entity
Predicate shipCommanded P884 FINISHED
Object CSS Sumter 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: CSS Sumter | Statement: [Raphael Semmes, shipCommanded, CSS Sumter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CSS Sumter
Context triple: [Raphael Semmes, shipCommanded, CSS Sumter]
  • A. CSS Sumter chosen
    CSS Sumter was a Confederate commerce raider during the American Civil War, known for disrupting Union merchant shipping early in the conflict.
  • B. Summerton, South Carolina
    Summerton, South Carolina is a small town in Clarendon County known for its rural character and role in the historic Briggs v. Elliott school desegregation case.
  • C. University of South Carolina Sumter
    The University of South Carolina Sumter is a regional public campus of the University of South Carolina system offering two-year and select four-year degree programs to students in the Sumter area.
  • D. Summit, South Carolina
    Summit, South Carolina is a small rural town located in Lexington County within the Columbia metropolitan area.
  • E. Spartanburg Community College
    Spartanburg Community College is a public two-year institution offering associate degrees, certificates, and workforce training programs serving Spartanburg and the surrounding region.
  • 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_69e0b4ffac148190bbade9f0eceb660b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fbe31cec8190a1007414148b8abe completed April 21, 2026, 4:24 a.m.
Created at: April 16, 2026, 1:49 p.m.