Triple
T14287980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horseshoe Falls |
E354227
|
entity |
| Predicate | erosionRate |
P113629
|
FINISHED |
| Object | historically several feet per year |
—
|
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: historically several feet per year | Statement: [Horseshoe Falls, erosionRate, historically several feet per year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: erosionRate Context triple: [Horseshoe Falls, erosionRate, historically several feet per year]
-
A.
erosionAgent
Indicates the natural force or process responsible for wearing away, transporting, or reshaping material from a surface.
-
B.
erosionResistance
Indicates how strongly one entity can withstand or prevent being worn away, degraded, or removed by erosive forces caused by another entity or the environment.
-
C.
hasErosionFeature
Indicates that one entity exhibits or contains a specific erosion-related feature or form resulting from erosional processes.
-
D.
eroded
Indicates that a force or process has gradually worn away, diminished, or degraded something over time.
-
E.
cliffStability
Indicates the degree to which a cliff is structurally secure and resistant to collapse or erosion under current conditions.
- 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_69d8278e17088190b328c5a9d4be74ff |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de698023288190b1d705235c2b2ca3 |
completed | April 14, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69de2a88446481909cd526da97a3b70f |
completed | April 14, 2026, 11:52 a.m. |
| PDg | Predicate description generation | batch_69de2e07d1f88190bdcd20967e484718 |
completed | April 14, 2026, 12:07 p.m. |
Created at: April 10, 2026, 1:11 a.m.