Triple

T2695857
Position Surface form Disambiguated ID Type / Status
Subject Charles Longley E58508 entity
Predicate father P120 FINISHED
Object John Longley
John Longley is the son of Charles Longley, who served as Archbishop of Canterbury in the 19th century.
 E290464 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: John Longley | Statement: [Charles Longley, father, John Longley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Longley
Context triple: [Charles Longley, father, John Longley]
  • A. Stephen Trott
    Stephen Trott is an American lawyer and former federal official who later served as a judge on the U.S. Court of Appeals for the Ninth Circuit.
  • B. David J. Wetherall
    David J. Wetherall is a computer scientist and academic known for his influential work and textbooks in computer networking.
  • C. Nigel Shadbolt
    Nigel Shadbolt is a British computer scientist and artificial intelligence researcher known for his leading role in promoting open data and digital governance.
  • D. Barton Myers
    Barton Myers is a Canadian-American architect renowned for his innovative urban infill projects and prominent cultural and civic buildings across North America.
  • E. Matthew C. Brown
    Matthew C. Brown is a film producer known for his work on the horror movie "Spectral."
  • 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: John Longley
Triple: [Charles Longley, father, John Longley]
Generated description
John Longley is the son of Charles Longley, who served as Archbishop of Canterbury in the 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: John Longley
Target entity description: John Longley is the son of Charles Longley, who served as Archbishop of Canterbury in the 19th century.
  • A. Stephen Trott
    Stephen Trott is an American lawyer and former federal official who later served as a judge on the U.S. Court of Appeals for the Ninth Circuit.
  • B. David J. Wetherall
    David J. Wetherall is a computer scientist and academic known for his influential work and textbooks in computer networking.
  • C. Nigel Shadbolt
    Nigel Shadbolt is a British computer scientist and artificial intelligence researcher known for his leading role in promoting open data and digital governance.
  • D. Barton Myers
    Barton Myers is a Canadian-American architect renowned for his innovative urban infill projects and prominent cultural and civic buildings across North America.
  • E. Matthew C. Brown
    Matthew C. Brown is a film producer known for his work on the horror movie "Spectral."
  • 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_69ab4ac269e481909cb317d79e68b75b completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abda2f7bf88190a1e3103dd014d871 completed March 7, 2026, 7:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69afaf6aa78c8190b57be36042008361 completed March 10, 2026, 5:43 a.m.
NEDg Description generation batch_69afb01b48508190a9b668a7273ad422 completed March 10, 2026, 5:46 a.m.
NED2 Entity disambiguation (via description) batch_69afb09133788190862d4b24d77facc0 completed March 10, 2026, 5:48 a.m.
Created at: March 6, 2026, 9:55 p.m.