Triple

T4053745
Position Surface form Disambiguated ID Type / Status
Subject Mataram E84644 entity
Predicate near P350 FINISHED
Object Merapi volcano E22001 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: Merapi volcano | Statement: [Mataram, near, Merapi volcano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Merapi volcano
Context triple: [Mataram, near, Merapi volcano]
  • A. Mount Merapi chosen
    Mount Merapi is one of Indonesia’s most active and dangerous stratovolcanoes, located on the island of Java near the city of Yogyakarta.
  • B. Mount Kelud
    Mount Kelud is an active stratovolcano in Indonesia known for its explosive eruptions and significant impact on the surrounding East Java region.
  • C. Galunggung volcano
    Galunggung volcano is an active stratovolcano in West Java, Indonesia, known for its explosive 1982 eruption that significantly disrupted regional air traffic.
  • D. Ekarma Volcano
    Ekarma Volcano is an active stratovolcano forming the uninhabited island of Ekarma in the central Kuril Islands chain of the northwest Pacific.
  • E. Samalas volcano
    Samalas volcano is a large stratovolcano on Indonesia’s Lombok Island whose massive 13th-century eruption is considered one of the most powerful volcanic events of the last millennium.
  • 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_69aed933bec881909edfa28ebb69c634 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefba878a48190a2e234d775215938 completed March 9, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5565b268c81908a3ef1f56bfcd657 completed March 14, 2026, 12:36 p.m.
Created at: March 9, 2026, 3:37 p.m.