Triple
T20692885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Merbabu |
E508594
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Mount Ungaran |
—
|
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: Mount Ungaran | Statement: [Mount Merbabu, locatedNear, Mount Ungaran]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Ungaran Context triple: [Mount Merbabu, locatedNear, Mount Ungaran]
-
A.
Mount Ungaran
chosen
Mount Ungaran is a stratovolcano in Central Java, Indonesia, known for its scenic hiking trails and the nearby ancient Gedong Songo Hindu temple complex.
-
B.
Mount Empung
Mount Empung is an active stratovolcano in North Sulawesi, Indonesia, forming a twin volcanic complex with the adjacent Mount Lokon.
-
C.
Mount Welirang
Mount Welirang is an active stratovolcano in East Java, Indonesia, known for its sulfur mining and frequent fumarolic activity.
-
D.
Mount Jagungal
Mount Jagungal is a prominent peak in New South Wales’ Snowy Mountains, known for its remote alpine landscapes and popularity with hikers and backcountry skiers.
-
E.
Mount Paku
Mount Paku is a small volcanic peak and popular scenic lookout located near the coastal town of Tairua on New Zealand’s Coromandel Peninsula.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c10fc4088190ab71ef078600954b |
completed | April 21, 2026, 12:13 a.m. |
Created at: April 16, 2026, 12:09 p.m.