Triple

T15553013
Position Surface form Disambiguated ID Type / Status
Subject Kaytetye people E370798 entity
Predicate traditionalLanguage P6149 FINISHED
Object Kaytetye language
The Kaytetye language is an Australian Aboriginal language of the Arandic family spoken by the Kaytetye people of the Northern Territory.
 E1163643 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: Kaytetye language | Statement: [Kaytetye people, traditionalLanguage, Kaytetye language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kaytetye language
Context triple: [Kaytetye people, traditionalLanguage, Kaytetye language]
  • A. Kayeli language
    The Kayeli language is an Austronesian language once spoken on Buru Island in Indonesia, now critically endangered or possibly extinct.
  • B. Yatye language
    The Yatye language is a lesser-known Niger-Congo language spoken by a small community in Nigeria, belonging to the Idomoid branch.
  • C. Eket language
    The Eket language is a Niger-Congo language spoken by the Eket people of Akwa Ibom State in southeastern Nigeria.
  • D. Agutaynen language
    Agutaynen is an Austronesian language spoken by the Agutaynen people of Palawan in the Philippines.
  • E. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • 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: Kaytetye language
Triple: [Kaytetye people, traditionalLanguage, Kaytetye language]
Generated description
The Kaytetye language is an Australian Aboriginal language of the Arandic family spoken by the Kaytetye people of the Northern Territory.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kaytetye language
Target entity description: The Kaytetye language is an Australian Aboriginal language of the Arandic family spoken by the Kaytetye people of the Northern Territory.
  • A. Kayeli language
    The Kayeli language is an Austronesian language once spoken on Buru Island in Indonesia, now critically endangered or possibly extinct.
  • B. Yatye language
    The Yatye language is a lesser-known Niger-Congo language spoken by a small community in Nigeria, belonging to the Idomoid branch.
  • C. Eket language
    The Eket language is a Niger-Congo language spoken by the Eket people of Akwa Ibom State in southeastern Nigeria.
  • D. Agutaynen language
    Agutaynen is an Austronesian language spoken by the Agutaynen people of Palawan in the Philippines.
  • E. Kavalan language
    The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a96c0c88190808f68601a36b506 completed April 16, 2026, 2:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4560008c81908ebd278c3dc45045 completed May 9, 2026, 2:32 p.m.
NEDg Description generation batch_69ff47aa0bb081908f67e9dae9bc7b27 completed May 9, 2026, 2:41 p.m.
NED2 Entity disambiguation (via description) batch_69ff480d81b881908eb3a51f1e7280b0 completed May 9, 2026, 2:43 p.m.
Created at: April 10, 2026, 4:09 a.m.