Triple
T5159156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terni |
E116389
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Marmore Falls |
E499448
|
NE 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: Marmore Falls | Statement: [Terni, hasLandmark, Marmore Falls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marmore Falls Context triple: [Terni, hasLandmark, Marmore Falls]
-
A.
Marmore Falls
chosen
Marmore Falls is a famous man-made waterfall in Umbria, Italy, known for its impressive height and scenic beauty.
-
B.
Bridal Veil Falls
Bridal Veil Falls is a picturesque waterfall on Manitoulin Island in Ontario, Canada, known for its curtain-like cascade and popular swimming and hiking area.
-
C.
Bridal Veil Falls
Bridal Veil Falls is the smallest of the three main waterfalls that make up Niagara Falls, located on the American side between Luna Island and Goat Island.
-
D.
Upper Falls
Upper Falls is a village and neighborhood within the city of Newton, Massachusetts, known for its historic mill district along the Charles River.
-
E.
Wahclella Falls
Wahclella Falls is a picturesque two-tiered waterfall on Tanner Creek in Oregon, popular for its short hiking trail and lush Columbia River Gorge scenery.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd445edb3881909b93b34d260717fc |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7904457c819090f382029ebb2b43 |
completed | March 20, 2026, 4:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bee07283c08190a8fc23d3041275ee |
completed | March 21, 2026, 6:16 p.m. |
Created at: March 20, 2026, 1:44 p.m.