Triple
T12791090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City water tunnels |
E305760
|
entity |
| Predicate | waterTypeConveyed |
P851
|
FINISHED |
| Object | treated drinking water |
—
|
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: treated drinking water | Statement: [New York City water tunnels, waterTypeConveyed, treated drinking water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterTypeConveyed Context triple: [New York City water tunnels, waterTypeConveyed, treated drinking water]
-
A.
waterType
chosen
Indicates the specific kind or category of water associated with an entity (e.g., fresh, salt, brackish).
-
B.
waterVolume
Indicates the amount of water present in or associated with an entity, typically measured as a volume.
-
C.
inflowWatercourse
Indicates that one watercourse flows into or feeds another water body or watercourse.
-
D.
waterDivertedFrom
Indicates that water is intentionally redirected or channeled away from one source, path, or location to another.
-
E.
waterFlowRate
Indicates the rate at which water moves or is transported through a given point or system over time.
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e6b55248190ab938e69eb263612 |
completed | April 10, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69d9640ba0688190973e4e7ec8d4a8e0 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:30 p.m.