Triple

T17680687
Position Surface form Disambiguated ID Type / Status
Subject Assistant United States Attorneys for the District of South Carolina E440758 entity
Predicate officeLocationsInclude P128547 FINISHED
Object Columbia, South Carolina NE NERFINISHED

How this triple was built (3 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: Columbia, South Carolina | Statement: [Assistant United States Attorneys for the District of South Carolina, officeLocationsInclude, Columbia, South Carolina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Columbia, South Carolina
Context triple: [Assistant United States Attorneys for the District of South Carolina, officeLocationsInclude, Columbia, South Carolina]
  • A. Columbia, South Carolina chosen
    Columbia, South Carolina is the capital and largest city of South Carolina, known for its role as a regional center of government, education, and culture.
  • B. Georgetown, South Carolina
    Georgetown, South Carolina is a historic coastal city and port in the southeastern United States known for its role in the rice trade and its well-preserved waterfront district.
  • C. Anderson, South Carolina
    Anderson, South Carolina is a small city in the northwestern part of the state known as the "Electric City," serving as a regional hub for manufacturing, healthcare, and education near Lake Hartwell.
  • D. Jefferson, South Carolina
    Jefferson, South Carolina is a small rural town in northeastern South Carolina known for its close-knit community and agricultural surroundings.
  • E. Williams, South Carolina
    Williams, South Carolina is a small rural town located in Colleton County in the southern part of the state.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: officeLocationsInclude
Context triple: [Assistant United States Attorneys for the District of South Carolina, officeLocationsInclude, Columbia, South Carolina]
  • A. includedOffice
    Indicates that one office is contained within, or forms part of, another office or organizational unit.
  • B. collectorOfficeLocation
    Indicates the physical office location associated with a particular collector.
  • C. addressesOffice
    Indicates that one entity directs communication, correspondence, or attention specifically to an office associated with another entity.
  • D. officeDeskLocation
    Indicates the specific desk or workstation location assigned to or used by an entity within an office space.
  • E. officeIsIn
    Indicates that one office is located within or inside another specified place or building.
  • F. None of above. chosen

Provenance (4 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e470445b3881908bb0930b986089f7 completed April 19, 2026, 6:03 a.m.
PD Predicate disambiguation batch_69e3cde3673c8190a889e14ba1f07dc1 completed April 18, 2026, 6:30 p.m.
PDg Predicate description generation batch_69e3cfaac2b881909e1140339eb1a0dd completed April 18, 2026, 6:38 p.m.
Created at: April 10, 2026, 10:01 a.m.