Triple

T22568079
Position Surface form Disambiguated ID Type / Status
Subject David Driskell E558005 entity
Predicate familyName P18 FINISHED
Object Driskell
Driskell is a surname most notably associated with David Driskell, a prominent American artist, scholar, and curator of African American art.
 E1542885 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: Driskell | Statement: [David Driskell, familyName, Driskell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Driskell
Context triple: [David Driskell, familyName, Driskell]
  • A. Calvin Gaines
    Calvin Gaines is an American songwriter and producer best known for his work in R&B and pop music, including co-writing Destiny’s Child’s hit “Say My Name.”
  • B. Derrick
    Derrick is the given name of Derrick Rose, an American professional basketball player and former NBA MVP.
  • C. Derrick
    Derrick is a Slytherin student at Hogwarts who plays on the house Quidditch team, known for his rough and aggressive style on the field.
  • D. Derrick
    "Derrick" is a long-running German crime television series that follows Inspector Stephan Derrick and his assistant Harry Klein as they investigate murder cases in and around Munich.
  • E. Darrick Moore
    Darrick Moore is a former collegiate wrestler recognized as a notable alumnus of the Princeton Tigers wrestling program.
  • 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: Driskell
Triple: [David Driskell, familyName, Driskell]
Generated description
Driskell is a surname most notably associated with David Driskell, a prominent American artist, scholar, and curator of African American art.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Driskell
Target entity description: Driskell is a surname most notably associated with David Driskell, a prominent American artist, scholar, and curator of African American art.
  • A. Calvin Gaines
    Calvin Gaines is an American songwriter and producer best known for his work in R&B and pop music, including co-writing Destiny’s Child’s hit “Say My Name.”
  • B. Derrick
    Derrick is a Slytherin student at Hogwarts who plays on the house Quidditch team, known for his rough and aggressive style on the field.
  • C. Derrick
    Derrick is the given name of Derrick Rose, an American professional basketball player and former NBA MVP.
  • D. Derrick
    "Derrick" is a long-running German crime television series that follows Inspector Stephan Derrick and his assistant Harry Klein as they investigate murder cases in and around Munich.
  • E. Darrick Moore
    Darrick Moore is a former collegiate wrestler recognized as a notable alumnus of the Princeton Tigers wrestling program.
  • 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_69e11e5ae4ac8190b1f503457603d969 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15fabb9f081908c33c8e2ddf18047 completed April 29, 2026, 1:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b2d7325dc8190b207d175b8e80d42 completed May 18, 2026, 3:17 p.m.
NEDg Description generation batch_6a0b364801cc81908204a937c1099728 completed May 18, 2026, 3:54 p.m.
NED2 Entity disambiguation (via description) batch_6a0b37998f888190bb53c2429760321a completed May 18, 2026, 4 p.m.
Created at: April 16, 2026, 8:52 p.m.