Triple
T17351293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savica Waterfall |
E421817
|
entity |
| Predicate | lowerHeight |
P53990
|
FINISHED |
| Object | about 25 meters |
—
|
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: about 25 meters | Statement: [Savica Waterfall, lowerHeight, about 25 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowerHeight Context triple: [Savica Waterfall, lowerHeight, about 25 meters]
-
A.
lowerLocation
Indicates that one entity is located physically below or at a lower vertical position relative to another entity.
-
B.
lowerTierHeight
chosen
Indicates the vertical measurement or elevation of the lower tier in a multi-level structure relative to a reference level.
-
C.
lowFloor
Indicates that something has a floor positioned close to ground level, allowing easy, step-free access.
-
D.
lowerStage
Indicates that one entity is at a lower or earlier stage, level, or phase in a progression or hierarchy than another entity.
-
E.
hasLow
Indicates that an entity possesses a value, level, or amount of something that is below a defined or expected threshold.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a2ca0708190aae8306ec3a6f2a7 |
completed | April 19, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69e3b02662d08190a07d0fb5c04b6f33 |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:44 a.m.