Triple
T7051211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minahasa Peninsula |
E163768
|
entity |
| Predicate | hasVolcano |
P6356
|
FINISHED |
| Object | Mount Lokon |
E310529
|
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 Lokon | Statement: [Minahasa Peninsula, hasVolcano, Mount Lokon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Lokon Context triple: [Minahasa Peninsula, hasVolcano, Mount Lokon]
-
A.
Mount Lokon
chosen
Mount Lokon is an active stratovolcano in North Sulawesi, Indonesia, known for its frequent eruptions and significant volcanic activity.
-
B.
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.
-
C.
Mount Talang
Mount Talang is an active stratovolcano in Indonesia known for its frequent eruptions and location near the city of Padang in West Sumatra.
-
D.
Mount Wanggameti
Mount Wanggameti is the tallest mountain on the Indonesian island of Sumba, known for its forested slopes and biodiversity within protected conservation areas.
-
E.
Mount Welirang
Mount Welirang is an active stratovolcano in East Java, Indonesia, known for its sulfur mining and frequent fumarolic activity.
- 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_69c7d372ca248190bd5aa6b1648199f2 |
completed | March 28, 2026, 1:11 p.m. |
Created at: March 27, 2026, 2:37 p.m.