Triple

T2675904
Position Surface form Disambiguated ID Type / Status
Subject Alexander Haig E56458 entity
Predicate familyName P18 FINISHED
Object Haig E113685 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: Haig | Statement: [Alexander Haig, familyName, Haig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haig
Context triple: [Alexander Haig, familyName, Haig]
  • A. Haig chosen
    "Haig" is a biographical work by Duff Cooper that chronicles the life and military career of British Field Marshal Douglas Haig, a key commander during World War I.
  • B. Viscount Gort
    Viscount Gort is a British peerage title most famously associated with John Vereker, the World War II military commander who led the British Expeditionary Force during the Battle of France.
  • C. Julian Byng
    Julian Byng was a British Army officer and First World War general who later served as Governor General of Canada.
  • D. Outram
    Outram is a central district in Singapore known for its major medical facilities, heritage architecture, and proximity to the downtown core.
  • E. Outram
    Outram is an English surname historically associated with several notable figures, including British military officers and public servants.
  • 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_69ab4a4b13fc81909dfdb3f23da46832 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd9b3530c819093942cc985f814ef completed March 7, 2026, 7:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69afa0638a9c8190b48ca5aa56eb66ff completed March 10, 2026, 4:38 a.m.
Created at: March 6, 2026, 9:54 p.m.