Triple
T16885551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karapiro Dam |
E421529
|
entity |
| Predicate | createsLakeUsedFor |
P28866
|
FINISHED |
| Object | rowing |
—
|
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: rowing | Statement: [Karapiro Dam, createsLakeUsedFor, rowing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createsLakeUsedFor Context triple: [Karapiro Dam, createsLakeUsedFor, rowing]
-
A.
createsLake
Indicates that one entity causes the formation or existence of a lake in relation to another entity or location.
-
B.
usesLakeFor
chosen
Indicates that an entity utilizes a lake as a resource or setting for some purpose, activity, or function.
-
C.
hasLakeThatRecreates
Indicates that an entity possesses or is associated with a lake that reproduces, simulates, or recreates certain conditions, features, or experiences.
-
D.
usedToCreateLand
Indicates that something served as a means, material, or method for producing or forming a particular piece of land.
-
E.
hasLakeThatRepresents
Indicates a relationship where a lake serves as a symbolic or representative feature for something, such as a place, concept, or entity.
- 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_69d889d470fc8190b4aec199636c0c56 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3bbc00cf8819088a08ddb00cd3c96 |
completed | April 18, 2026, 5:13 p.m. |
| PD | Predicate disambiguation | batch_69e32b90ec3c819099c51bb7baf2984c |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:29 a.m.