Triple

T20039506
Position Surface form Disambiguated ID Type / Status
Subject Bon Secours Wellness Arena E497372 entity
Predicate city P40 FINISHED
Object Greenville
Greenville is a mid-sized city in South Carolina known for its revitalized downtown, cultural attractions, and role as a regional economic hub.
E698869 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: Greenville | Statement: [Bon Secours Wellness Arena, city, Greenville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greenville
Context triple: [Bon Secours Wellness Arena, city, Greenville]
  • A. Greenville
    Greenville is a small city in south-central Alabama known for its historic downtown and role as the county seat of Butler County.
  • B. Greenville
    Greenville is a village and census-designated place in the town of Smithfield in Providence County, Rhode Island, known for its suburban character and historic New England charm.
  • C. Greenville
    Greenville is a suburban community within the greater Dallas metropolitan area in Texas.
  • D. Greenville
    Greenville is a small city located in western Kentucky, serving as a local hub within the rural Pennyrile region.
  • E. Greenville
    Greenville is a residential neighborhood in the southern part of Jersey City, New Jersey, known for its diverse community and urban character.
  • 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: Greenville
Triple: [Bon Secours Wellness Arena, city, Greenville]
Generated description
Greenville is a mid-sized city in South Carolina known for its revitalized downtown, cultural attractions, and role as a regional economic hub.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Greenville
Target entity description: Greenville is a mid-sized city in South Carolina known for its revitalized downtown, cultural attractions, and role as a regional economic hub.
  • A. Greenville chosen
    Greenville is a mid-sized city in the northwestern part of South Carolina known for its revitalized downtown, cultural amenities, and role as an economic hub in the Upstate region.
  • B. Greenville
    Greenville is a city in eastern North Carolina known as a regional hub for education, healthcare, and culture.
  • C. Greenville
    Greenville is a small city in south-central Alabama known for its historic downtown and role as the county seat of Butler County.
  • D. Greenville
    Greenville is a small city in southern Illinois known for its historic downtown and as the home of Greenville University.
  • E. Greenville
    Greenville is a small city located in western Kentucky, serving as a local hub within the rural Pennyrile region.
  • F. None of above.

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_69da627278c88190babe4297a9df1236 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e662eae538819083c74d7a2ab493d2 completed April 20, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0843d6af4881909dcbebe764b7bb6c completed May 16, 2026, 10:15 a.m.
NEDg Description generation batch_6a0844730ce88190b63395a365a46c34 completed May 16, 2026, 10:18 a.m.
NED2 Entity disambiguation (via description) batch_6a0844f2ad4081908e7a901d4e9a941d completed May 16, 2026, 10:20 a.m.
Created at: April 11, 2026, 3:36 p.m.