Triple

T20079113
Position Surface form Disambiguated ID Type / Status
Subject Frank Hurley E499949 entity
Predicate placeOfDeath P21 FINISHED
Object Australia NE NERFINISHED

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: Australia | Statement: [Frank Hurley, placeOfDeath, Australia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Australia
Context triple: [Frank Hurley, placeOfDeath, Australia]
  • A. Australia chosen
    Australia is a large island continent and sovereign country in the Southern Hemisphere, known for its unique wildlife, diverse landscapes, and major cities such as Sydney and Melbourne.
  • B. Australia II
    Australia II is the Australian racing yacht that famously ended the New York Yacht Club’s 132-year winning streak by capturing the America’s Cup in 1983.
  • C. Burpengary
    Burpengary is a rapidly growing suburban town in Queensland, Australia, located north of Brisbane and known for its residential communities and local commercial centres.
  • D. Aus
    Aus is a small town in southern Namibia known for its desert landscapes, World War I history, and nearby feral horses.
  • E. Australes
    Australes is the French name for the Austral Islands, a remote archipelago in French Polynesia known for its small communities and traditional Polynesian culture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6643e216c819088c002fc1de2772a completed April 20, 2026, 5:37 p.m.
Created at: April 11, 2026, 3:40 p.m.