Triple

T21625782
Position Surface form Disambiguated ID Type / Status
Subject Wik-Mungkan E533696 entity
Predicate hasLinguisticArea P17400 FINISHED
Object Cape York Peninsula linguistic area
The Cape York Peninsula linguistic area is a region in northern Australia where diverse Aboriginal languages, including Wik-Mungkan, share convergent structural and lexical features due to long-term contact.
E1494580 NE FINISHED

How this triple was built (4 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: Cape York Peninsula linguistic area | Statement: [Wik-Mungkan, hasLinguisticArea, Cape York Peninsula linguistic area]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cape York Peninsula linguistic area
Context triple: [Wik-Mungkan, hasLinguisticArea, Cape York Peninsula linguistic area]
  • A. 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.
  • B. Southeast Australia linguistic area
    The Southeast Australia linguistic area is a region of southeastern Australia characterized by a set of shared structural and typological features among diverse Aboriginal languages that have arisen through long-term contact and convergence.
  • C. Yirrkala region
    The Yirrkala region is a culturally and spiritually significant area in northeast Arnhem Land, Australia, central to the traditions, law, and ceremonial life of the Yolngu people.
  • D. Pilbara cultural bloc
    The Pilbara cultural bloc is a broad Indigenous cultural region in Western Australia encompassing diverse Aboriginal groups, languages, and traditions associated with the Pilbara area.
  • E. Arnhem Land
    Arnhem Land is a vast, remote region in Australia’s Northern Territory known for its strong Aboriginal culture, traditional land ownership, and largely untouched wilderness.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cape York Peninsula linguistic area
Triple: [Wik-Mungkan, hasLinguisticArea, Cape York Peninsula linguistic area]
Generated description
The Cape York Peninsula linguistic area is a region in northern Australia where diverse Aboriginal languages, including Wik-Mungkan, share convergent structural and lexical features due to long-term contact.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cape York Peninsula linguistic area
Target entity description: The Cape York Peninsula linguistic area is a region in northern Australia where diverse Aboriginal languages, including Wik-Mungkan, share convergent structural and lexical features due to long-term contact.
  • A. 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.
  • B. Southeast Australia linguistic area
    The Southeast Australia linguistic area is a region of southeastern Australia characterized by a set of shared structural and typological features among diverse Aboriginal languages that have arisen through long-term contact and convergence.
  • C. Yirrkala region
    The Yirrkala region is a culturally and spiritually significant area in northeast Arnhem Land, Australia, central to the traditions, law, and ceremonial life of the Yolngu people.
  • D. Pilbara cultural bloc
    The Pilbara cultural bloc is a broad Indigenous cultural region in Western Australia encompassing diverse Aboriginal groups, languages, and traditions associated with the Pilbara area.
  • E. Arnhem Land
    Arnhem Land is a vast, remote region in Australia’s Northern Territory known for its strong Aboriginal culture, traditional land ownership, and largely untouched wilderness.
  • F. None of above. chosen

Provenance (5 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_69e0c464fba881908d0ff2ac80511ce1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef52131f2c8190b9966adf43a0fe4f completed April 27, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a0f92ff3881908f6319ef93abf078 completed May 17, 2026, 6:57 p.m.
NEDg Description generation batch_6a0a10106ab4819096045effbbdfe95e completed May 17, 2026, 6:59 p.m.
NED2 Entity disambiguation (via description) batch_6a0a10c8c5bc8190add0ee63eb338964 completed May 17, 2026, 7:02 p.m.
Created at: April 16, 2026, 6:34 p.m.