Triple
T18201850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Decade Volcanoes |
E435808
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Merapi |
—
|
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: Merapi | Statement: [Decade Volcanoes, hasMember, Merapi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Merapi Context triple: [Decade Volcanoes, hasMember, Merapi]
-
A.
Mount Merapi
chosen
Mount Merapi is one of Indonesia’s most active and dangerous stratovolcanoes, located on the island of Java near the city of Yogyakarta.
-
B.
Galunggung volcano
Galunggung volcano is an active stratovolcano in West Java, Indonesia, known for its explosive 1982 eruption that significantly disrupted regional air traffic.
-
C.
Mount Kelud
Mount Kelud is an active stratovolcano in Indonesia known for its explosive eruptions and significant impact on the surrounding East Java region.
-
D.
Sumbing volcano
Sumbing volcano is a prominent stratovolcano in Central Java, Indonesia, known for its high peak and fertile surrounding agricultural lands.
-
E.
Mount Karangetang
Mount Karangetang is an active stratovolcano in North Sulawesi, Indonesia, known as one of the country’s most frequently erupting and hazardous volcanoes.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e0d71f288190918ca78543118bbe |
completed | April 19, 2026, 2:04 p.m. |
Created at: April 10, 2026, 10:32 a.m.