Triple
T26746238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brooklyn and Staten Island |
E674409
|
entity |
| Predicate | shareWaterSupply |
P179451
|
FINISHED |
| Object | New York City water system |
—
|
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: New York City water system | Statement: [Brooklyn and Staten Island, shareWaterSupply, New York City water system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shareWaterSupply Context triple: [Brooklyn and Staten Island, shareWaterSupply, New York City water system]
-
A.
waterSupplyShare
Indicates the proportion of a total water supply that is allocated to or used by a particular entity.
-
B.
sharesWaterAccess
chosen
Indicates that two or more entities use or have rights to the same source or system of water access.
-
C.
shareWaterway
Indicates that two or more entities are connected by and have access to the same navigable body of water, such as a river, canal, or sea route.
-
D.
sourceOfWaterSupply
Indicates that one entity serves as the origin or provider of another entity’s water supply.
-
E.
waterSource
Indicates that one entity serves as the source or provider of water for another 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_69eecda63a3881908095c47900692e65 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69fbc36ce1f88190a7fa1656b714e107 |
completed | May 6, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69fbbd13595c81908719f52c3d37a7e8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: April 27, 2026, 3:51 a.m.