Triple
T25334947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Amsterdam |
E635250
|
entity |
| Predicate | locatedNearRiverMouth |
P28855
|
FINISHED |
| Object | Berbice River |
—
|
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: Berbice River | Statement: [New Amsterdam, locatedNearRiverMouth, Berbice River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedNearRiverMouth Context triple: [New Amsterdam, locatedNearRiverMouth, Berbice River]
-
A.
riverMouthAt
Indicates that the mouth or endpoint of a river is located at a specified place or geographic feature.
-
B.
locatedInRiverArea
Indicates that one entity is situated within the geographic area occupied by, adjacent to, or directly associated with a particular river.
-
C.
locatedOnBankOfRiver
Indicates that one entity is situated along or directly adjacent to the bank of a specified river.
-
D.
riverMouthRegion
Indicates the region or area where a river flows into a larger body of water, such as a sea, lake, or another river.
-
E.
hasEstuaryNear
chosen
Indicates that the estuary of a water body is located in close proximity to a specified place or feature.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 21, 2026, 1:32 p.m.