Triple
T21828767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sakonnet River Bridge |
E538928
|
entity |
| Predicate | isInWaterBodySystem |
P63896
|
FINISHED |
| Object | Narragansett Bay watershed |
—
|
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: Narragansett Bay watershed | Statement: [Sakonnet River Bridge, isInWaterBodySystem, Narragansett Bay watershed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInWaterBodySystem Context triple: [Sakonnet River Bridge, isInWaterBodySystem, Narragansett Bay watershed]
-
A.
isInlandWaterBodyOf
Indicates that one water body is an inland (non-oceanic) water feature that is geographically part of, contained within, or associated with another entity.
-
B.
isInlandWaterBody
Indicates that one entity is a body of water located inland (such as a lake, river, or reservoir) rather than part of the open ocean or sea.
-
C.
locatedInWaterBodyType
Indicates that an entity is situated within or on a body of water of a specified type (e.g., lake, river, ocean).
-
D.
isInWaterwaySystem
chosen
Indicates that an entity is part of, contained within, or traverses a particular waterway network or system.
-
E.
inWaterBodyRegion
Indicates that an entity is located within a specific region or area of a water body.
- 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_69e0c475cda88190987d08f23caebdc1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f091344c848190b1675432a8c255f2 |
completed | April 28, 2026, 10:51 a.m. |
| PD | Predicate disambiguation | batch_69e6be815a108190be81d7c987d0c0d6 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:54 p.m.