Triple
T29857656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harlem watershed |
E758229
|
entity |
| Predicate | channelsWaterTo |
P14199
|
FINISHED |
| Object | larger connected water bodies |
—
|
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: larger connected water bodies | Statement: [Harlem watershed, channelsWaterTo, larger connected water bodies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: channelsWaterTo Context triple: [Harlem watershed, channelsWaterTo, larger connected water bodies]
-
A.
waterFlowsThrough
Indicates that water moves along a path or channel passing from one location or object to another.
-
B.
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.
-
C.
hasWaterChannel
Indicates that one entity possesses or contains a channel or conduit through which water flows or is transported.
-
D.
transportsWaterTo
chosen
Indicates that one entity carries or conveys water from its location or source to another entity or destination.
-
E.
managesWaterFrom
Indicates that one entity is responsible for controlling, directing, or handling water originating from 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_69f2245b4dec8190b85f664d918a00a5 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6768345fc8190bdc72aa7af054375 |
completed | May 2, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f66ac32b60819092290b2de35988d3 |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 29, 2026, 5:47 p.m.