Triple

T12836121
Position Surface form Disambiguated ID Type / Status
Subject Ann Todd E306917 entity
Predicate spouse P13 FINISHED
Object Victor Saville E157178 NE FINISHED

How this triple was built (2 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: Victor Saville | Statement: [Ann Todd, spouse, Victor Saville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Victor Saville
Context triple: [Ann Todd, spouse, Victor Saville]
  • A. Victor Saville chosen
    Victor Saville was a British film director and producer known for his work in both the UK and Hollywood during the early to mid-20th century.
  • B. George Levick
    George Levick was a British Royal Navy surgeon, Antarctic explorer, and photographer best known for his role in Scott’s Terra Nova Expedition and his pioneering observations of penguin behavior.
  • C. Ernest Sefton
    Ernest Sefton was an author whose work inspired the film "The Clairvoyant."
  • D. Philip Stainton
    Philip Stainton was a British character actor known for his supporting roles in mid-20th-century films, including the adventure drama "Mogambo."
  • E. Alfred Lambert
    Alfred Lambert is the ailing Midwestern patriarch whose decline and complex family relationships drive much of the emotional and thematic core of Jonathan Franzen’s novel "The Corrections."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96ff015f4819090070a01f3938acc completed April 10, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68edaa6288190a775f6e852fa941b completed May 2, 2026, 11:55 p.m.
Created at: April 9, 2026, 5:35 p.m.