Triple
T7051213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minahasa Peninsula |
E163768
|
entity |
| Predicate | hasVolcano |
P6356
|
FINISHED |
| Object | Mount Soputan |
E320097
|
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: Mount Soputan | Statement: [Minahasa Peninsula, hasVolcano, Mount Soputan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Soputan Context triple: [Minahasa Peninsula, hasVolcano, Mount Soputan]
-
A.
Mount Soputan
chosen
Mount Soputan is an active stratovolcano located on the northern arm of Sulawesi in Indonesia, known for its frequent explosive eruptions.
-
B.
Mount Welirang
Mount Welirang is an active stratovolcano in East Java, Indonesia, known for its sulfur mining and frequent fumarolic activity.
-
C.
Mount Loke
Mount Loke is a peak in Antarctica’s Olympus Range, part of the McMurdo Dry Valleys region known for its cold, arid, and largely ice-free landscape.
-
D.
Mount Sibayak
Mount Sibayak is an active stratovolcano in North Sumatra, Indonesia, known for its accessible crater, geothermal vents, and popular hiking trails near the town of Berastagi.
-
E.
Mount Nanlaud
Mount Nanlaud is the tallest mountain on the Micronesian island of Pohnpei, known for its lush tropical rainforest and frequent cloud cover.
- 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_69c6885f598c8190b6b6495c59d8d962 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e2500570819087200013d859cfe6 |
completed | March 27, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c79c857ca08190a964861cb7aff86a |
completed | March 28, 2026, 9:16 a.m. |
Created at: March 27, 2026, 2:37 p.m.