Triple

T20926341
Position Surface form Disambiguated ID Type / Status
Subject Awabakal E515353 entity
Predicate hasDocumentedLanguageWork P43659 FINISHED
Object An Australian Grammar of the Language, as Spoken by the Aborigines of the Hunter River, Lake Macquarie, &c. NE NERFINISHED

How this triple was built (3 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: An Australian Grammar of the Language, as Spoken by the Aborigines of the Hunter River, Lake Macquarie, &c. | Statement: [Awabakal, hasDocumentedLanguageWork, An Australian Grammar of the Language, as Spoken by the Aborigines of the Hunter River, Lake Macquarie, &c.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: An Australian Grammar of the Language, as Spoken by the Aborigines of the Hunter River, Lake Macquarie, &c.
Context triple: [Awabakal, hasDocumentedLanguageWork, An Australian Grammar of the Language, as Spoken by the Aborigines of the Hunter River, Lake Macquarie, &c.]
  • A. An Australian Grammar of the Language, as Spoken by the Aborigines, in the Vicinity of Hunter’s River, Lake Macquarie, &c. chosen
    "An Australian Grammar of the Language, as Spoken by the Aborigines, in the Vicinity of Hunter’s River, Lake Macquarie, &c." is a 19th-century grammatical description and vocabulary of the Awabakal Aboriginal language of New South Wales, Australia.
  • B. Arnhem Land linguistic area
    The Arnhem Land linguistic area is a region in northern Australia characterized by a group of Aboriginal languages that share extensive structural and lexical features due to long-term contact and cultural interaction.
  • C. Yolngu Matha
    Yolngu Matha is a group of closely related Indigenous Australian languages spoken by the Yolngu people of northeastern Arnhem Land in the Northern Territory.
  • D. Dyirbal language
    Dyirbal language is an Australian Aboriginal language traditionally spoken in northeastern Queensland, noted for its complex noun class system and distinctive grammatical structures.
  • E. Bininj Kunwok dialect continuum
    The Bininj Kunwok dialect continuum is a group of closely related Aboriginal languages spoken by Bininj people in western Arnhem Land in Australia, encompassing several mutually intelligible dialects such as Kunwinjku.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasDocumentedLanguageWork
Context triple: [Awabakal, hasDocumentedLanguageWork, An Australian Grammar of the Language, as Spoken by the Aborigines of the Hunter River, Lake Macquarie, &c.]
  • A. hasWorkedInLanguage
    Indicates that an entity has performed work or professional activities using a particular language.
  • B. hasLinguisticDocumentation chosen
    Indicates that there exists recorded linguistic information or documentation about the language or linguistic properties of the subject.
  • C. hasWorkedOnLanguageFamily
    Indicates that an entity (such as a person or organization) has conducted work, research, or professional activity related to a particular language family.
  • D. hasOfficialLanguageOfWork
    Indicates that an entity uses a specified language as its official medium for conducting work or formal activities.
  • E. usesWorkingLanguagesOf
    Indicates that one entity employs or operates using the working languages associated with another entity.
  • F. None of above.

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_69e0b4fb431c8190b9d40e6a72f0cc87 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6f65200b08190ac208204a20f5a6a completed April 21, 2026, 4 a.m.
PD Predicate disambiguation batch_69e5c9af1fe08190953366a466950140 completed April 20, 2026, 6:37 a.m.
Created at: April 16, 2026, 12:49 p.m.