Triple
T30722957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Los Milagros Aqueduct |
E782201
|
entity |
| Predicate | startPointOfWaterSupply |
P4360
|
FINISHED |
| Object | Proserpina Reservoir |
—
|
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: Proserpina Reservoir | Statement: [Los Milagros Aqueduct, startPointOfWaterSupply, Proserpina Reservoir]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startPointOfWaterSupply Context triple: [Los Milagros Aqueduct, startPointOfWaterSupply, Proserpina Reservoir]
-
A.
sourceOfWaterSupply
chosen
Indicates that one entity serves as the origin or provider of another entity’s water supply.
-
B.
waterSourceDedicatedTo
Indicates that a particular water source is specifically allocated or reserved for a designated use, group, or purpose.
-
C.
waterSource
Indicates that one entity serves as the source or provider of water for another entity.
-
D.
waterSourceSystem
Indicates a system that supplies, manages, or distributes water as a source for use by other entities.
-
E.
waterSupplyPopulationServed
Indicates the number of people that are provided with or served by a particular water supply system.
- 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_69f224acd24481908ed5f96f0d69b5dd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fef3ceef648190b58027c93d757438 |
completed | May 9, 2026, 8:43 a.m. |
| PD | Predicate disambiguation | batch_69fef359da2c819091a034387b08821f |
completed | May 9, 2026, 8:42 a.m. |
Created at: April 29, 2026, 8:36 p.m.