Triple

T12344212
Position Surface form Disambiguated ID Type / Status
Subject Armstrong-Jones E294306 entity
Predicate componentSurname P5298 FINISHED
Object Jones
Jones is a common English surname shared by numerous notable individuals across fields such as politics, sports, science, and the arts.
E46350 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: Jones | Statement: [Armstrong-Jones, componentSurname, Jones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jones
Context triple: [Armstrong-Jones, componentSurname, Jones]
  • A. John
    John is the given first name of the legendary American professional golfer Byron Nelson, one of the sport’s early great champions.
  • B. John
    John is the given name of the influential American blues singer, songwriter, and guitarist John Lee Hooker.
  • C. John
    John of Cornwall was a 12th-century Cornish scholar and theologian known for his Latin writings and contributions to medieval intellectual life.
  • D. John
    John is the given name of John Albert William Spencer-Churchill, a British aristocrat and 10th Duke of Marlborough.
  • E. John
    John is the middle name of Alexander John Buckley Ford.
  • 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: Jones
Triple: [Armstrong-Jones, componentSurname, Jones]
Generated description
Jones is a common English surname shared by numerous notable individuals across fields such as politics, sports, science, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jones
Target entity description: Jones is a common English surname shared by numerous notable individuals across fields such as politics, sports, science, and the arts.
  • A. Jones chosen
    Jones is a common English-language surname borne by numerous notable individuals across fields such as entertainment, sports, politics, and science.
  • B. John
    John is the given name of the British philosopher of language J. L. Austin, known for developing speech act theory.
  • C. John
    John is the given name of Saint John of Rila, a revered Bulgarian hermit and the most prominent saint of the Bulgarian Orthodox Church.
  • D. John
    John is the given name of John Philip Holland, the Irish engineer known for developing some of the first practical submarines.
  • E. John
    John of Cornwall was a 12th-century Cornish scholar and theologian known for his Latin writings and contributions to medieval intellectual life.
  • 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_69d6ab6ccbec8190b09e2d357aa80064 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f78a970819086beec3e4da8c49e completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62aac9edc8190ab1740d23af1b250 completed May 2, 2026, 4:47 p.m.
NEDg Description generation batch_69f62c55aacc8190a0544306825bdfab completed May 2, 2026, 4:54 p.m.
NED2 Entity disambiguation (via description) batch_69f62d4d0b8881908aa6b67db7d14609 completed May 2, 2026, 4:58 p.m.
Created at: April 8, 2026, 9:53 p.m.