Triple
T11327115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harlem River Ship Canal |
E268248
|
entity |
| Predicate | replacedWaterBody |
P21976
|
FINISHED |
| Object | original Spuyten Duyvil Creek |
—
|
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: original Spuyten Duyvil Creek | Statement: [Harlem River Ship Canal, replacedWaterBody, original Spuyten Duyvil Creek]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedWaterBody Context triple: [Harlem River Ship Canal, replacedWaterBody, original Spuyten Duyvil Creek]
-
A.
connectedBodyOfWater
Indicates that two geographic locations are linked by a continuous body of water through which water can flow between them.
-
B.
waterBodyCreated
chosen
Indicates that one entity is responsible for the formation or creation of a particular body of water.
-
C.
bodyOfWater
Indicates that one entity is a body of water that is geographically or physically associated with another entity.
-
D.
associatedBodyOfWaterFormerName
Indicates that a body of water is linked to another name it was known by in the past.
-
E.
waterbodyID
Indicates a unique identifier that links an entity to a specific body of water.
- 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_69d6aacb1f0881908c84a349fd1be047 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9e2253881909518cad0f12ef612 |
completed | April 9, 2026, 6:03 p.m. |
| PD | Predicate disambiguation | batch_69d787ad575081908274280bf75d95fd |
completed | April 9, 2026, 11:04 a.m. |
Created at: April 8, 2026, 9:32 p.m.