Triple

T34795352
Position Surface form Disambiguated ID Type / Status
Subject R v Penguin Books Ltd E1003061 entity
Predicate prosecutingCounsel P57571 FINISHED
Object Mervyn Griffith-Jones
Mervyn Griffith-Jones was a British barrister and judge best known for leading the prosecution in the landmark 1960 obscenity trial over D. H. Lawrence’s novel "Lady Chatterley’s Lover."
 E2128637 NE FINISHED

How this triple was built (3 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: Mervyn Griffith-Jones | Statement: [R v Penguin Books Ltd, prosecutingCounsel, Mervyn Griffith-Jones]
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: Mervyn Griffith-Jones
Triple: [R v Penguin Books Ltd, prosecutingCounsel, Mervyn Griffith-Jones]
Generated description
Mervyn Griffith-Jones was a British barrister and judge best known for leading the prosecution in the landmark 1960 obscenity trial over D. H. Lawrence’s novel "Lady Chatterley’s Lover."
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: prosecutingCounsel
Context triple: [R v Penguin Books Ltd, prosecutingCounsel, Mervyn Griffith-Jones]
  • A. counselForProsecution chosen
    Indicates that an entity serves as a legal representative or advisor acting on behalf of the prosecution in a legal proceeding.
  • B. prosecutingAuthority
    Indicates that an entity serves as the official body responsible for bringing and conducting legal proceedings against another party in a criminal or regulatory case.
  • C. prosecutorSought
    Indicates that a prosecutor actively pursued or requested a particular legal action, charge, or outcome against a party.
  • D. prosecuted
    Indicates that legal authorities have formally brought criminal charges against an entity and pursued a case against them in a court of law.
  • E. subsequentProsecutor
    Indicates that one prosecutor follows or succeeds another in handling the same or a related legal case.
  • F. None of above.

Provenance (6 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_69f76db543808190b188c6c86a91491b completed May 3, 2026, 3:45 p.m.
NER Named-entity recognition batch_69f77a83ec9081909309bc3d646f193c completed May 3, 2026, 4:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a37fafadfe481908e2b2f54745308d5 completed June 21, 2026, 2:53 p.m.
NEDg Description generation batch_6a37fbd574a48190bea1f7942d54ec3a completed June 21, 2026, 2:57 p.m.
NED2 Entity disambiguation (via description) batch_6a37fc58434c819095b89e724f748bd6 completed June 21, 2026, 2:59 p.m.
PD Predicate disambiguation batch_69f7795b1abc8190823664d1caa94649 completed May 3, 2026, 4:35 p.m.
Created at: May 3, 2026, 3:59 p.m.