Triple

T8911980
Position Surface form Disambiguated ID Type / Status
Subject George Sassoon E212204 entity
Predicate name P16 FINISHED
Object George Sassoon E212204 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 Sassoon | Statement: [George Sassoon, name, George Sassoon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Sassoon
Context triple: [George Sassoon, name, George Sassoon]
  • A. George Sassoon chosen
    George Sassoon was a British linguist, engineer, and writer, known as the son and literary executor of war poet Siegfried Sassoon.
  • B. Vyner Brooke
    Vyner Brooke was the third and last White Rajah of Sarawak, ruling the kingdom until its cession to Britain after World War II.
  • C. Herbert Ward
    Herbert Ward was a British sculptor, illustrator, and writer known for his depictions of African subjects and contributions to late 19th-century illustrated literature.
  • D. Arthur Lyttelton
    Arthur Lyttelton was a 19th-century English Anglican clergyman and academic who became the first Master of Selwyn College, Cambridge.
  • E. Andrew Hulme
    Andrew Hulme is a British film editor known for his work on feature films such as the crime thriller "Lucky Number Slevin."
  • 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_69ca8393b1808190bd4336787ffa2c40 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6525d1408190a76522d7c4ac37da completed April 1, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba3c92c481909589e6a3c9469136 completed April 3, 2026, 1:01 p.m.
Created at: March 30, 2026, 6:55 p.m.