Triple

T20308419
Position Surface form Disambiguated ID Type / Status
Subject Sedang people E510165 entity
Predicate nativeLanguage P151 FINISHED
Object Sedang language 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: Sedang language | Statement: [Sedang people, nativeLanguage, Sedang language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sedang language
Context triple: [Sedang people, nativeLanguage, Sedang language]
  • A. Sedang language chosen
    The Sedang language is an Austroasiatic language spoken by the Sedang people of Vietnam’s Central Highlands, closely related to other Bahnaric and Mon-Khmer languages.
  • B. Semendo language
    The Semendo language is an Austronesian language spoken by the Semendo ethnic group in southern Sumatra, Indonesia.
  • C. Madura language
    The Madura language is an Austronesian language spoken primarily on Madura Island and in parts of East Java, Indonesia, by the Madurese people.
  • D. Dimasa language
    Dimasa is a Tibeto-Burman language spoken primarily by the Dimasa people in the Indian states of Assam and Nagaland.
  • E. Zande language
    The Zande language is a Central African language spoken primarily by the Azande people across parts of South Sudan, the Central African Republic, and the Democratic Republic of the Congo.
  • 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_69e0b4c7491c8190961113c4283b10b0 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e677411cf08190ba7e98a4135b643a completed April 20, 2026, 6:58 p.m.
Created at: April 16, 2026, 11:18 a.m.