Triple

T21966847
Position Surface form Disambiguated ID Type / Status
Subject DBP E542479 entity
Predicate nativeName P15 FINISHED
Object Dewan Bahasa dan Pustaka 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: Dewan Bahasa dan Pustaka | Statement: [DBP, nativeName, Dewan Bahasa dan Pustaka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dewan Bahasa dan Pustaka
Context triple: [DBP, nativeName, Dewan Bahasa dan Pustaka]
  • A. Tatabahasa Dewan
    Tatabahasa Dewan is an authoritative Malay grammar reference book widely used in Malaysia for standardizing and teaching the Malay language.
  • B. Badan Bahasa
    Badan Bahasa is Indonesia’s official government body responsible for developing, standardizing, and promoting the Indonesian language.
  • C. Dewan Bahasa dan Pustaka (Malaysia) chosen
    Dewan Bahasa dan Pustaka (Malaysia) is a Malaysian government institution responsible for developing, standardizing, and promoting the Malay language and its literature.
  • D. Lembaga Budi
    Lembaga Budi is a philosophical and ethical work by Indonesian scholar and writer Buya Hamka that explores moral values and character formation in an Islamic context.
  • E. National Library of Indonesia
    The National Library of Indonesia is the country’s central library institution in Jakarta, serving as the primary repository for Indonesia’s written cultural heritage and national bibliographic collections.
  • 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_69e0c47fab1081908dc74a6545dbb051 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1245b821c8190816058c2a07707a3 completed April 28, 2026, 9:19 p.m.
Created at: April 16, 2026, 8:01 p.m.