Triple

T226327
Position Surface form Disambiguated ID Type / Status
Subject Wilson E4321 entity
Predicate hasCognate P2525 FINISHED
Object Willis
Willis is a masculine given name and surname of English origin, often considered a variant or cognate of the name Wilson.
 E31141 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: Willis | Statement: [Wilson, hasCognate, Willis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Willis
Context triple: [Wilson, hasCognate, Willis]
  • A. Sullivan
    Sullivan is a shortened name for the international law firm Sullivan & Worcester LLP, known for its corporate, tax, and financial legal services.
  • B. Roscoe
    "Roscoe" is an essay by Washington Irving, included in his collection *The Sketch Book of Geoffrey Crayon, Gent.*, that reflects on the life and character of English historian and writer William Roscoe.
  • C. Peabody
    Peabody is a suburban city in northeastern Massachusetts known for its location on the North Shore and its historical ties to the leather industry.
  • D. Pierce
    Pierce is a surname most prominently associated with Paul Pierce, the Hall of Fame former NBA star of the Boston Celtics.
  • E. Addison
    Addison is a small, business-focused town in the Dallas–Fort Worth metropolitan area known for its dense concentration of restaurants, corporate offices, and frequent special events.
  • 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: Willis
Triple: [Wilson, hasCognate, Willis]
Generated description
Willis is a masculine given name and surname of English origin, often considered a variant or cognate of the name Wilson.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Willis
Target entity description: Willis is a masculine given name and surname of English origin, often considered a variant or cognate of the name Wilson.
  • A. Sullivan
    Sullivan is a shortened name for the international law firm Sullivan & Worcester LLP, known for its corporate, tax, and financial legal services.
  • B. Roscoe
    "Roscoe" is an essay by Washington Irving, included in his collection *The Sketch Book of Geoffrey Crayon, Gent.*, that reflects on the life and character of English historian and writer William Roscoe.
  • C. Peabody
    Peabody is a suburban city in northeastern Massachusetts known for its location on the North Shore and its historical ties to the leather industry.
  • D. Pierce
    Pierce is a surname most prominently associated with Paul Pierce, the Hall of Fame former NBA star of the Boston Celtics.
  • E. Addison
    Addison is a small, business-focused town in the Dallas–Fort Worth metropolitan area known for its dense concentration of restaurants, corporate offices, and frequent special events.
  • 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_69a257363ffc81909757bde7ab3404da completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c8d97d08190ad7c1c3e9322f34c completed Feb. 28, 2026, 3:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3695b4f648190969ed240f1597866 completed Feb. 28, 2026, 10:16 p.m.
NEDg Description generation batch_69a369ec7d4481909dcdb53082806239 completed Feb. 28, 2026, 10:19 p.m.
NED2 Entity disambiguation (via description) batch_69a36a6714208190bf021994a84d0163 completed Feb. 28, 2026, 10:21 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.