Triple
T30047274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arena, New York |
E763488
|
entity |
| Predicate | locatedInReservoirSystem |
P138976
|
FINISHED |
| Object | New York City water supply system |
—
|
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: New York City water supply system | Statement: [Arena, New York, locatedInReservoirSystem, New York City water supply system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInReservoirSystem Context triple: [Arena, New York, locatedInReservoirSystem, New York City water supply system]
-
A.
reservoirLocation
Indicates that a reservoir is geographically located at or within a specified place or region.
-
B.
reservoir
Indicates that one entity serves as a storage or containment source (often for a resource) that can supply or affect another entity.
-
C.
inReservoirSystem
chosen
Indicates that one entity is part of, contained within, or managed by a particular reservoir system.
-
D.
hasReservoirOnTributary
Indicates that a reservoir is located on a tributary of a main water body rather than on the main water body itself.
-
E.
reservoirAlsoKnownAs
Indicates that a reservoir is referred to by an alternative name or alias.
- 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_69f22470a89c8190be7273297c0e0d19 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a008d6085508190a71c52cd028a6297 |
completed | May 10, 2026, 1:51 p.m. |
| PD | Predicate disambiguation | batch_6a008ced31448190b8fc60bf87b40647 |
completed | May 10, 2026, 1:49 p.m. |
Created at: April 29, 2026, 6:54 p.m.