Triple

T17626892
Position Surface form Disambiguated ID Type / Status
Subject Aka-Jeru language E429868 entity
Predicate family P566 FINISHED
Object Ongan 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: Ongan | Statement: [Aka-Jeru language, family, Ongan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ongan
Context triple: [Aka-Jeru language, family, Ongan]
  • A. Ongan chosen
    Ongan is a small language family comprising the indigenous Andamanese languages spoken primarily in the southern Andaman Islands of India.
  • B. Ong
    Ong is a common Chinese surname, particularly among Hokkien and Teochew speakers, often representing the Mandarin surname "Wang."
  • C. Ondong
    Ondong is the main administrative and urban center of Kepulauan Sitaro Regency in North Sulawesi, Indonesia.
  • D. Narungga
    Narungga are an Aboriginal Australian people and language group traditionally associated with the Yorke Peninsula in South Australia.
  • E. Osing
    Osing is an Austronesian language spoken primarily by the Osing people in the eastern part of Java, Indonesia.
  • 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46dbd122c8190a5db8c0088c81034 completed April 19, 2026, 5:53 a.m.
Created at: April 10, 2026, 5:52 a.m.