Triple
T21390223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toccoa Creek |
E527622
|
entity |
| Predicate | hasWaterfallHeightAtToccoaFalls |
P47584
|
FINISHED |
| Object | approximately 186 feet |
—
|
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: approximately 186 feet | Statement: [Toccoa Creek, hasWaterfallHeightAtToccoaFalls, approximately 186 feet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWaterfallHeightAtToccoaFalls Context triple: [Toccoa Creek, hasWaterfallHeightAtToccoaFalls, approximately 186 feet]
-
A.
VirginiaFallsRelativeHeight
Indicates the relative vertical drop or height of Virginia Falls compared to a reference point or other waterfalls.
-
B.
heightAboveFalls
Indicates that one entity is located at a higher elevation than a waterfall or waterfalls associated with another entity.
-
C.
waterfallHeight
chosen
Indicates the vertical distance or drop in elevation from the top to the bottom of a waterfall.
-
D.
upperFallsHeight
Indicates the vertical height measurement of the upper falls section in a waterfall or multi-tiered cascade.
-
E.
approximateHeightOfFallsViewed
Indicates the estimated vertical height of the waterfalls as observed or perceived by the viewer.
- 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_69e0b51ff3748190935c0a513c62a12b |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b112a7808190ae4b180ce0d2b408 |
completed | April 22, 2026, 11:29 a.m. |
| PD | Predicate disambiguation | batch_69e6162bbfc88190a3e75859941b2638 |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 5:13 p.m.