Triple

T19708493
Position Surface form Disambiguated ID Type / Status
Subject Sir Robert Megarry E473276 entity
Predicate name P16 FINISHED
Object Robert Megarry
Robert Megarry was a prominent British judge and legal scholar known for his influential work in property law and equity.
E1392426 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: Robert Megarry | Statement: [Sir Robert Megarry, name, Robert Megarry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Megarry
Context triple: [Sir Robert Megarry, name, Robert Megarry]
  • A. Thomas Christie
    Thomas Christie was an 18th-century British physician, political writer, and radical intellectual known for his involvement in reformist circles and contributions to periodical literature.
  • B. Jean Grahame
    Jean Grahame is the mother of American actress Gloria Grahame, known for her work in classic Hollywood cinema.
  • C. Alex Farquharson
    Alex Farquharson is a British curator and museum director best known for leading major contemporary art institutions in the UK.
  • D. Walter Connolly
    Walter Connolly was an American character actor of the 1930s known for his comic and often blustery supporting roles in Hollywood films.
  • E. John Applegate
    John Applegate was a 19th-century American pioneer and explorer associated with the development of overland emigrant routes in the western United States.
  • 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: Robert Megarry
Triple: [Sir Robert Megarry, name, Robert Megarry]
Generated description
Robert Megarry was a prominent British judge and legal scholar known for his influential work in property law and equity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robert Megarry
Target entity description: Robert Megarry was a prominent British judge and legal scholar known for his influential work in property law and equity.
  • A. Thomas Christie
    Thomas Christie was an 18th-century British physician, political writer, and radical intellectual known for his involvement in reformist circles and contributions to periodical literature.
  • B. Jean Grahame
    Jean Grahame is the mother of American actress Gloria Grahame, known for her work in classic Hollywood cinema.
  • C. Alex Farquharson
    Alex Farquharson is a British curator and museum director best known for leading major contemporary art institutions in the UK.
  • D. Walter Connolly
    Walter Connolly was an American character actor of the 1930s known for his comic and often blustery supporting roles in Hollywood films.
  • E. John Applegate
    John Applegate was a 19th-century American pioneer and explorer associated with the development of overland emigrant routes in the western United States.
  • 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e642bc754481908bdf5bfad069aec8 completed April 20, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07b4ea32d48190b94a6bbc52833db8 completed May 16, 2026, 12:06 a.m.
NEDg Description generation batch_6a07b5d90eb081909286da7f06d606cf completed May 16, 2026, 12:10 a.m.
NED2 Entity disambiguation (via description) batch_6a07b6bb60088190b3473ff2bf7cfde1 completed May 16, 2026, 12:13 a.m.
Created at: April 10, 2026, 1:46 p.m.