Triple
T2111089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City water supply system |
E42502
|
entity |
| Predicate | waterTreatmentCharacteristic |
P27141
|
FINISHED |
| Object | largely unfiltered surface 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: largely unfiltered surface water | Statement: [New York City water supply system, waterTreatmentCharacteristic, largely unfiltered surface water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterTreatmentCharacteristic Context triple: [New York City water supply system, waterTreatmentCharacteristic, largely unfiltered surface water]
-
A.
waterType
Indicates the specific kind or category of water associated with an entity (e.g., fresh, salt, brackish).
-
B.
waterCondition
chosen
Indicates the state or quality of water affecting an entity, such as its cleanliness, safety, or suitability for a particular use.
-
C.
drinkingWaterStandard
Indicates that something meets an established quality or safety standard for drinking water.
-
D.
hydrologicalCharacteristic
Indicates a relationship where a hydrological feature or condition (such as water flow, level, or behavior) characterizes or describes another entity.
-
E.
waterQualityUse
Indicates the way in which water quality is evaluated, classified, or applied for specific purposes or uses.
- 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_69a8871040f08190aac2e2d0ab6b47ad |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbb024ce88190a30e1320e53b82bc |
completed | March 7, 2026, 5:43 a.m. |
| PD | Predicate disambiguation | batch_69abb7ba08948190a3c236bb53ee4257 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.