Triple

T11699511
Position Surface form Disambiguated ID Type / Status
Subject Ponsonby family E278083 entity
Predicate hasMember P10 FINISHED
Object Myles Ponsonby
Myles Ponsonby was a British diplomat and member of the aristocratic Ponsonby family.
E939738 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: Myles Ponsonby | Statement: [Ponsonby family, hasMember, Myles Ponsonby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Myles Ponsonby
Context triple: [Ponsonby family, hasMember, Myles Ponsonby]
  • A. Murray Hone
    Murray Hone is a Canadian former professional hockey player best known for his past marriage to actress Evangeline Lilly.
  • B. Henry Edward Napier
    Henry Edward Napier was a 19th-century British naval officer and historian, best known for his multi-volume history of Florence.
  • C. William Ponsonby
    William Ponsonby was a prominent late 16th-century London publisher and bookseller known for issuing major literary works of the Elizabethan era.
  • D. William Bickerton
    William Bickerton was a 19th-century Latter Day Saint leader and founder of the Church of Jesus Christ (Bickertonite), a Restorationist Christian denomination.
  • E. Roger Whittaker
    Roger Whittaker was a Kenyan-born British singer-songwriter and whistler known for his smooth baritone voice and easy-listening folk and pop songs such as "Durham Town" and "The Last Farewell."
  • 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: Myles Ponsonby
Triple: [Ponsonby family, hasMember, Myles Ponsonby]
Generated description
Myles Ponsonby was a British diplomat and member of the aristocratic Ponsonby family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Myles Ponsonby
Target entity description: Myles Ponsonby was a British diplomat and member of the aristocratic Ponsonby family.
  • A. Murray Hone
    Murray Hone is a Canadian former professional hockey player best known for his past marriage to actress Evangeline Lilly.
  • B. Henry Edward Napier
    Henry Edward Napier was a 19th-century British naval officer and historian, best known for his multi-volume history of Florence.
  • C. William Ponsonby
    William Ponsonby was a prominent late 16th-century London publisher and bookseller known for issuing major literary works of the Elizabethan era.
  • D. William Bickerton
    William Bickerton was a 19th-century Latter Day Saint leader and founder of the Church of Jesus Christ (Bickertonite), a Restorationist Christian denomination.
  • E. Roger Whittaker
    Roger Whittaker was a Kenyan-born British singer-songwriter and whistler known for his smooth baritone voice and easy-listening folk and pop songs such as "Durham Town" and "The Last Farewell."
  • 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_69d6aafe02d881909900d54ad7d4af84 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a47df68c81908a91919a69b4880d completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef147e2e10819085eaed83fd955b6b completed April 27, 2026, 7:47 a.m.
NEDg Description generation batch_69ef3553a1748190b554463bcea8bd1d completed April 27, 2026, 10:07 a.m.
NED2 Entity disambiguation (via description) batch_69ef51fe3824819099f440426d3e6888 completed April 27, 2026, 12:09 p.m.
Created at: April 8, 2026, 9:40 p.m.