Triple

T16074369
Position Surface form Disambiguated ID Type / Status
Subject Lorna Doone E389943 entity
Predicate narratorCharacter P17575 FINISHED
Object John Ridd
John Ridd is the steadfast West Country farmer and protagonist of R.D. Blackmore’s novel "Lorna Doone," known for his courage, loyalty, and enduring love for Lorna.
E1192261 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 Ridd | Statement: [Lorna Doone, narratorCharacter, John Ridd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Ridd
Context triple: [Lorna Doone, narratorCharacter, John Ridd]
  • A. Isaac Booth
    Isaac Booth was an architect best known for designing the landmark Wainhouse Tower in Halifax, England.
  • B. Samuel Wake
    Samuel Wake was a British sea captain after whom the remote Pacific atoll Wake Island was named.
  • C. James Stoker
    James Stoker is a person known primarily for sharing the surname associated with notable figures such as author Bram Stoker.
  • D. William Freake
    William Freake was a prominent 19th-century British property developer and builder known for creating large parts of South Kensington and other affluent areas of London.
  • E. Charles Byrne
    Charles Byrne is an American publisher best known as a co-founder of Berkley Books, a major mass-market paperback imprint.
  • 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 Ridd
Triple: [Lorna Doone, narratorCharacter, John Ridd]
Generated description
John Ridd is the steadfast West Country farmer and protagonist of R.D. Blackmore’s novel "Lorna Doone," known for his courage, loyalty, and enduring love for Lorna.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John Ridd
Target entity description: John Ridd is the steadfast West Country farmer and protagonist of R.D. Blackmore’s novel "Lorna Doone," known for his courage, loyalty, and enduring love for Lorna.
  • A. Isaac Booth
    Isaac Booth was an architect best known for designing the landmark Wainhouse Tower in Halifax, England.
  • B. Samuel Wake
    Samuel Wake was a British sea captain after whom the remote Pacific atoll Wake Island was named.
  • C. James Stoker
    James Stoker is a person known primarily for sharing the surname associated with notable figures such as author Bram Stoker.
  • D. William Freake
    William Freake was a prominent 19th-century British property developer and builder known for creating large parts of South Kensington and other affluent areas of London.
  • E. Charles Byrne
    Charles Byrne is an American publisher best known as a co-founder of Berkley Books, a major mass-market paperback imprint.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183c0e4388190b4b9b86e1c38f184 completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe48715e48190a493d1e373dc7c5f completed May 10, 2026, 1:51 a.m.
NEDg Description generation batch_69ffe5407d408190b6c5ac22f2e62026 completed May 10, 2026, 1:54 a.m.
NED2 Entity disambiguation (via description) batch_69ffe5d294c88190b60b9654899b5149 completed May 10, 2026, 1:56 a.m.
Created at: April 10, 2026, 4:57 a.m.