Triple

T17331315
Position Surface form Disambiguated ID Type / Status
Subject Satsuma Peninsula E420821 entity
Predicate nearbyVolcano P10443 FINISHED
Object Sakurajima 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: Sakurajima | Statement: [Satsuma Peninsula, nearbyVolcano, Sakurajima]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sakurajima
Context triple: [Satsuma Peninsula, nearbyVolcano, Sakurajima]
  • A. Sakurajima chosen
    Sakurajima is an active stratovolcano in Kagoshima Prefecture, Japan, known for its frequent eruptions and dramatic presence in Kagoshima Bay.
  • B. Aso Volcano
    Aso Volcano is a massive active volcanic complex in Japan’s Kyushu region, known for having one of the world’s largest calderas and frequent eruptions.
  • C. Shinmoedake
    Shinmoedake is an active stratovolcano in Japan’s Kirishima mountain range, known for its explosive eruptions and scenic crater landscape.
  • D. Panari-jima
    Panari-jima is a small, remote island in Japan’s Yaeyama Islands, known for its pristine beaches, clear waters, and rich surrounding coral reefs.
  • E. Mount Asama
    Mount Asama is an active and prominent volcano in central Honshu, Japan, known for its frequent eruptions and status as one of the country’s most closely monitored peaks.
  • 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_69d889d3adc881909319f1edb8d2a956 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e439d6870c8190989897aa6beba8ff completed April 19, 2026, 2:11 a.m.
Created at: April 10, 2026, 5:43 a.m.