Triple

T2443858
Position Surface form Disambiguated ID Type / Status
Subject Levar Stoney E53341 entity
Predicate familyName P18 FINISHED
Object Stoney
Stoney is a surname most notably associated with Levar Stoney, the mayor of Richmond, Virginia.
E267464 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: Stoney | Statement: [Levar Stoney, familyName, Stoney]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stoney
Context triple: [Levar Stoney, familyName, Stoney]
  • A. Like a Stone
    "Like a Stone" is a melancholic, introspective rock ballad by Audioslave, renowned for Chris Cornell’s haunting vocals and reflective lyrics on mortality and longing.
  • B. Sticks & Stones
    Sticks & Stones is a 2019 stand-up comedy special by Dave Chappelle known for its provocative, boundary-pushing material and controversial social commentary.
  • C. Stonebwoy
    Stonebwoy is a Ghanaian dancehall and Afropop musician known for his influential role in modern African music and numerous award-winning hits.
  • D. Black Stone
    The Black Stone is a revered Islamic relic set into the eastern corner of the Kaaba in Mecca, which pilgrims traditionally try to touch or kiss during the Hajj and Umrah rituals.
  • E. Dusty
    Dusty is the nickname of Dusty Cohl, a prominent Canadian film producer and co-founder of the Toronto International Film Festival.
  • 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: Stoney
Triple: [Levar Stoney, familyName, Stoney]
Generated description
Stoney is a surname most notably associated with Levar Stoney, the mayor of Richmond, Virginia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Stoney
Target entity description: Stoney is a surname most notably associated with Levar Stoney, the mayor of Richmond, Virginia.
  • A. Like a Stone
    "Like a Stone" is a melancholic, introspective rock ballad by Audioslave, renowned for Chris Cornell’s haunting vocals and reflective lyrics on mortality and longing.
  • B. Sticks & Stones
    Sticks & Stones is a 2019 stand-up comedy special by Dave Chappelle known for its provocative, boundary-pushing material and controversial social commentary.
  • C. Stonebwoy
    Stonebwoy is a Ghanaian dancehall and Afropop musician known for his influential role in modern African music and numerous award-winning hits.
  • D. Black Stone
    The Black Stone is a revered Islamic relic set into the eastern corner of the Kaaba in Mecca, which pilgrims traditionally try to touch or kiss during the Hajj and Umrah rituals.
  • E. Dusty
    Dusty is the nickname of Dusty Cohl, a prominent Canadian film producer and co-founder of the Toronto International Film Festival.
  • 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_69ab495b6dac8190ac82661aa1452222 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abca22aa708190a1489234373cca65 completed March 7, 2026, 6:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0b768f8819084fb74a3a2643cb8 completed March 9, 2026, 4:09 p.m.
NEDg Description generation batch_69aef5de0e4c8190af460b7e2fb2a5eb completed March 9, 2026, 4:31 p.m.
NED2 Entity disambiguation (via description) batch_69aef68a6a18819097876fea0120103b completed March 9, 2026, 4:34 p.m.
Created at: March 6, 2026, 9:43 p.m.