Triple
T37854436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horseshoe Falls |
E944148
|
entity |
| Predicate | feedsWaterTo |
P92348
|
FINISHED |
| Object | Llangollen Canal |
—
|
NE NERFINISHED |
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: Llangollen Canal | Statement: [Horseshoe Falls, feedsWaterTo, Llangollen Canal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: feedsWaterTo Context triple: [Horseshoe Falls, feedsWaterTo, Llangollen Canal]
-
A.
feedsWaterfall
Indicates that one entity supplies or channels water into a waterfall, contributing to its flow.
-
B.
managesWaterFrom
Indicates that one entity is responsible for controlling, directing, or handling water originating from another entity.
-
C.
feedingHabitat
Indicates the type of environment or location where an organism typically obtains and consumes its food.
-
D.
feedsOrDrains
Indicates that one entity supplies resources or energy to another or removes them from it, acting as either a source (feeds) or a sink (drains).
-
E.
feedsViaAqueduct
chosen
Indicates that something supplies or channels a resource (typically water) to another thing through an aqueduct.
- 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_69f76eed4d9c81908b1b71ba9e3b61fe |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.