Triple
T15954581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purwokerto |
E386900
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Mount Slamet |
E650132
|
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 Slamet | Statement: [Purwokerto, near, Mount Slamet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Slamet Context triple: [Purwokerto, near, Mount Slamet]
-
A.
Mount Slamet
chosen
Mount Slamet is one of the highest and most active stratovolcanoes on the island of Java in Indonesia.
-
B.
Mount Wayang
Mount Wayang is a volcanic mountain in West Java, Indonesia, known for its geothermal activity and as part of the highland region that feeds major rivers in the area.
-
C.
Mount Batok
Mount Batok is a small, steep-sided volcanic cone in East Java, Indonesia, located near Mount Bromo within the Tengger caldera and known for its striking, photogenic profile.
-
D.
Mount Kapalatmada
Mount Kapalatmada is the tallest mountain on Buru Island in Indonesia, forming a prominent feature of the island’s rugged interior.
-
E.
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.
- 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156f94b108190905d295c3405860e |
completed | April 16, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffbe7c8ef081908fa6da7975c271f6 |
completed | May 9, 2026, 11:08 p.m. |
Created at: April 10, 2026, 4:53 a.m.