Triple

T6020358
Position Surface form Disambiguated ID Type / Status
Subject Samalas volcano E134046 entity
Predicate nearbySettlement P350 FINISHED
Object Mataram E113979 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: [Samalas volcano, nearbySettlement, Mataram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mataram
Context triple: [Samalas volcano, nearbySettlement, Mataram]
  • A. Mataram
    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 chosen
    Mataram is the capital and largest city of the Indonesian province of West Nusa Tenggara, located on the island of Lombok.
  • C. Semarapura
    Semarapura is the capital town of Bali’s Klungkung Regency, known for its traditional Balinese culture, historic royal court, and vibrant arts and markets.
  • D. Bima City
    Bima City is an urban municipality on the eastern part of Sumbawa Island in Indonesia, serving as a regional economic and cultural center.
  • E. Amlapura
    Amlapura is a town in eastern Bali, Indonesia, known as the main urban and cultural hub of the surrounding Karangasem area.
  • 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_69c008742a5c8190b9cb9c2787a3d8b3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04f86efec8190bc357dddf6ebb4a9 completed March 22, 2026, 8:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c12510695c8190a8c379c9802a9089 completed March 23, 2026, 11:33 a.m.
Created at: March 22, 2026, 4:07 p.m.