Triple
T6315319
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Andreas Dam |
E141599
|
entity |
| Predicate | associatedReservoirUse |
P40334
|
FINISHED |
| Object | emergency water storage |
—
|
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: emergency water storage | Statement: [San Andreas Dam, associatedReservoirUse, emergency water storage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedReservoirUse Context triple: [San Andreas Dam, associatedReservoirUse, emergency water storage]
-
A.
reservoirUse
chosen
Indicates the way a reservoir is utilized or the purpose for which its stored water is used.
-
B.
waterUse
Indicates the amount or manner in which water is consumed, utilized, or withdrawn by an entity or activity.
-
C.
hasWaterUse
Indicates a relationship where one entity utilizes or consumes water for a particular purpose, process, or function.
-
D.
reservoir
Indicates that one entity serves as a storage or containment source (often for a resource) that can supply or affect another entity.
-
E.
hasWatershedUse
Indicates that a particular type of use, activity, or function is associated with or applied to a watershed.
- 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_69c008d13b8c8190be47d896eb735605 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c064a197488190946c4637b3c829a5 |
completed | March 22, 2026, 9:52 p.m. |
| PD | Predicate disambiguation | batch_69c060e5efc48190861b8266e5b0cc0c |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:28 p.m.