Triple

T17217583
Position Surface form Disambiguated ID Type / Status
Subject Octopussy E417891 entity
Predicate screenwriter P2831 FINISHED
Object George MacDonald Fraser E538500 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: George MacDonald Fraser | Statement: [Octopussy, screenwriter, George MacDonald Fraser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George MacDonald Fraser
Context triple: [Octopussy, screenwriter, George MacDonald Fraser]
  • A. George MacDonald Fraser chosen
    George MacDonald Fraser was a Scottish author and screenwriter best known for his historical Flashman novels and his work on several major film adaptations.
  • B. Joseph MacDonald
    Joseph MacDonald was an American cinematographer known for his work on numerous classic Hollywood films, particularly in the 1940s and 1950s.
  • C. Philip MacDonald
    Philip MacDonald was a British-born novelist and screenwriter best known for his crime and mystery fiction and his contributions to classic Hollywood films.
  • D. Hamish Hamilton
    Hamish Hamilton is a renowned British publishing imprint known for literary fiction and non-fiction by prominent international authors.
  • E. Hamish Hamilton
    Hamish Hamilton is a British television director renowned for helming major live broadcasts, including high-profile award shows and music events.
  • 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42ddb2b148190b3b50572cc285e3d completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01675381a0819094ed04eac636440b completed May 11, 2026, 5:21 a.m.
Created at: April 10, 2026, 5:38 a.m.