Triple

T19320122
Position Surface form Disambiguated ID Type / Status
Subject Edith Alice Morrell E483199 entity
Predicate hasMedicalAttendant P135586 FINISHED
Object John Bodkin Adams NE NERFINISHED

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: John Bodkin Adams | Statement: [Edith Alice Morrell, hasMedicalAttendant, John Bodkin Adams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Bodkin Adams
Context triple: [Edith Alice Morrell, hasMedicalAttendant, John Bodkin Adams]
  • A. John Bodkin Adams chosen
    John Bodkin Adams was a British general practitioner suspected of being a serial killer in the 1940s and 1950s, whose controversial trial for the murder of an elderly patient became one of the most famous criminal cases in UK medical and legal history.
  • B. Sir Adrian Knox
    Sir Adrian Knox was an Australian lawyer and judge who served as the second Chief Justice of the High Court of Australia in the early 20th century.
  • C. Charles McNaughton
    Charles McNaughton was a British actor active in the early 20th century, known for his character roles in films and on stage.
  • D. Sir William Savile
    Sir William Savile was a 17th-century English politician and Royalist who served as a Member of Parliament and played a notable role in the events leading up to and during the English Civil War.
  • E. Hubert Lamb
    Hubert Lamb was a pioneering British climatologist best known for founding the Climatic Research Unit at the University of East Anglia and for his influential historical studies of climate variability.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasMedicalAttendant
Context triple: [Edith Alice Morrell, hasMedicalAttendant, John Bodkin Adams]
  • A. hasImmediateMedicalResponse
    Indicates that an entity receives prompt medical attention or intervention immediately following an incident or onset of a medical condition.
  • B. hasMedicalStaffApprox
    Indicates that an entity is associated with an approximate or estimated number of medical staff.
  • C. hasMedicalCenter
    Indicates that an entity possesses, hosts, or is associated with a medical center facility.
  • D. hasEmergencyCare
    Indicates that an entity provides or is equipped with emergency medical care services for another entity or individuals.
  • E. hasMedicalCorps
    Indicates that an entity possesses, maintains, or is associated with an organized medical corps or medical service unit.
  • F. None of above. chosen

Provenance (4 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_69d8e8d13e3c81909d91d1d5ec37c095 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e60d87a0088190a60201b1f388089e completed April 20, 2026, 11:27 a.m.
PD Predicate disambiguation batch_69e4dd0ef66881909d489d634eee817a completed April 19, 2026, 1:47 p.m.
PDg Predicate description generation batch_69e4e4709d4481908c280cdd2ac18977 completed April 19, 2026, 2:19 p.m.
Created at: April 10, 2026, 1:32 p.m.