Triple
T1019223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Merapi |
E22001
|
entity |
| Predicate | dangerLevel |
P3842
|
FINISHED |
| Object | one of Indonesia’s most dangerous volcanoes |
—
|
LITERAL 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: one of Indonesia’s most dangerous volcanoes | Statement: [Mount Merapi, dangerLevel, one of Indonesia’s most dangerous volcanoes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dangerLevel Context triple: [Mount Merapi, dangerLevel, one of Indonesia’s most dangerous volcanoes]
-
A.
riskLevel
chosen
Indicates the degree of potential harm, loss, or adverse outcome associated with a particular situation, action, or entity.
-
B.
difficulty
Indicates the level of challenge, complexity, or effort required to perform an action, solve a problem, or achieve a particular outcome.
-
C.
joyLevel
Indicates the degree or intensity of joy experienced or expressed by an entity.
-
D.
thrillLevel
Indicates the degree of excitement or intensity of exhilaration associated with an experience, action, or situation.
-
E.
endangerment
Indicates a relationship in which one entity exposes another to potential harm, risk, or danger.
- F. None of above.
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_69a493d6e380819097b384986ffc315c |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7dbcf7c8190858b2d16a27bd2ff |
completed | March 1, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69a4b7238d4c8190b22d6c2ac0ac4911 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.