Triple
T17241552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agam Regency |
E418509
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Mount Singgalang |
E418510
|
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 Singgalang | Statement: [Agam Regency, contains, Mount Singgalang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Singgalang Context triple: [Agam Regency, contains, Mount Singgalang]
-
A.
Mount Singgalang
chosen
Mount Singgalang is a dormant stratovolcano in West Sumatra, Indonesia, known for its twin-peaked profile and lush, cloud-forested slopes.
-
B.
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.
-
C.
Mount Welirang
Mount Welirang is an active stratovolcano in East Java, Indonesia, known for its sulfur mining and frequent fumarolic activity.
-
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 Dulang-dulang
Mount Dulang-dulang is one of the highest and most biodiverse peaks in the Philippines, located in the northern part of Mindanao.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e203ec88190a21f38cbb18a14fa |
completed | April 19, 2026, 1:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01793efa288190b63f641381566bb9 |
completed | May 11, 2026, 6:37 a.m. |
Created at: April 10, 2026, 5:39 a.m.