Triple
T27405599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harlem River Lift Bridge |
E691986
|
entity |
| Predicate | riverMouthSide |
P117934
|
FINISHED |
| Object | Harlem River Ship Canal vicinity |
—
|
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: Harlem River Ship Canal vicinity | Statement: [Harlem River Lift Bridge, riverMouthSide, Harlem River Ship Canal vicinity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverMouthSide Context triple: [Harlem River Lift Bridge, riverMouthSide, Harlem River Ship Canal vicinity]
-
A.
tributarySide
Indicates the side (e.g., left or right bank) of a main watercourse on which a tributary joins it.
-
B.
riverMouthType
Indicates the type or form of the feature where a river meets a larger body of water.
-
C.
watercourseSide
chosen
Indicates that one entity is located along or on the side of a particular watercourse, such as a river, stream, or canal.
-
D.
riverMouthBasin
Indicates that a river’s mouth lies within or drains into a particular drainage basin.
-
E.
riverMouthAt
Indicates that the mouth or endpoint of a river is located at a specified place or geographic 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_69ef5205fc808190ad3efc5525b8e6d6 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 27, 2026, 12:30 p.m.