Triple
T27023174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erawan National Park |
E680718
|
entity |
| Predicate | waterfallCharacteristic |
P172107
|
FINISHED |
| Object | multi-tiered waterfall |
—
|
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: multi-tiered waterfall | Statement: [Erawan National Park, waterfallCharacteristic, multi-tiered waterfall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterfallCharacteristic Context triple: [Erawan National Park, waterfallCharacteristic, multi-tiered waterfall]
-
A.
hasWaterCharacteristics
Indicates that one entity possesses qualities, properties, or behaviors characteristic of water.
-
B.
waterfallFlow
Indicates that water moves continuously downward over a vertical or steep drop, forming a waterfall-like flow between locations or surfaces.
-
C.
waterfallAlong
Indicates that a waterfall is located along the course, path, or extent of another geographic feature such as a river, trail, or boundary.
-
D.
hasWaterfall
Indicates that one entity possesses, contains, or features a waterfall associated with it.
-
E.
waterfallWidthApproximate
Indicates that the width of a waterfall is approximately a specified value, allowing for some margin of error rather than an exact measurement.
- F. None of above. chosen
Provenance (4 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_69eeeb5450988190bfc9a3c012ac463a |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6a9603b208190b3533ea2b441514c |
completed | May 3, 2026, 1:48 a.m. |
| PD | Predicate disambiguation | batch_69f6a751d5e48190a77dcecbe7ef9f0b |
completed | May 3, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f6a8de0b948190ae333e9cd99cbf6c |
completed | May 3, 2026, 1:46 a.m. |
Created at: April 27, 2026, 7:09 a.m.