Triple

T4178062
Position Surface form Disambiguated ID Type / Status
Subject Sanjaya dynasty E86525 entity
Predicate capital P234 FINISHED
Object Mataram E84644 NE FINISHED

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: Mataram | Statement: [Sanjaya dynasty, capital, Mataram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mataram
Context triple: [Sanjaya dynasty, capital, Mataram]
  • A. Mataram chosen
    Mataram was the principal urban and political center of the early Javanese Medang Kingdom, serving as a key hub of power and culture in central Java.
  • B. Mataram
    Mataram is the capital and largest city of the Indonesian province of West Nusa Tenggara, located on the island of Lombok.
  • C. Bajawa
    Bajawa is a small highland town in central Flores, Indonesia, known for its cool climate, traditional Ngada culture, and nearby volcanic and megalithic sites.
  • D. Denpasar
    Denpasar is the largest city and main economic and cultural hub on the Indonesian island of Bali.
  • E. Jember
    Jember is a regency and major urban center in eastern Java, Indonesia, known for its agricultural economy and cultural festivals such as the Jember Fashion Carnaval.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed93de98c8190ad838ce507b77c8a completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af02ec20fc8190b6f30576337e0ddc completed March 9, 2026, 5:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b589f2d7988190b59f0f119f66c046 completed March 14, 2026, 4:16 p.m.
Created at: March 9, 2026, 3:45 p.m.