Triple

T9901013
Position Surface form Disambiguated ID Type / Status
Subject Ypres 1917 E182281 entity
Predicate hasCommander P1197 FINISHED
Object Hubert Gough E233333 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: Hubert Gough | Statement: [Ypres 1917, hasCommander, Hubert Gough]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hubert Gough
Context triple: [Ypres 1917, hasCommander, Hubert Gough]
  • A. Hubert Gough chosen
    Hubert Gough was a British Army general of World War I, best known for his controversial leadership of the Fifth Army on the Western Front.
  • B. Frederick Stanley Maude
    Frederick Stanley Maude was a British Army general in World War I, best known for leading successful operations in Mesopotamia, including the capture of Baghdad in 1917.
  • C. Frederick Francis Maude
    Frederick Francis Maude was a British Army officer and recipient of the Victoria Cross for his actions during the Crimean War.
  • D. Richard Haldane
    Richard Haldane was a British Liberal statesman and lawyer best known for his major reforms of the British Army in the early 20th century.
  • E. Arthur Hill Griffith
    Arthur Hill Griffith was an Australian politician and public servant who played a significant role in the early 20th-century governance and development of New South Wales.
  • 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_69ca82876f8081909cf75df0f99bb13f completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cdb4e221448190b536742d1269f9d7 completed April 2, 2026, 12:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2577794d081909e852bda46f62988 completed April 5, 2026, 12:37 p.m.
Created at: March 30, 2026, 8:40 p.m.