Triple
T1091921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robbins Reef |
E24182
|
entity |
| Predicate | nearShippingLane |
P350
|
FINISHED |
| Object | main channel to Port of New York and New Jersey |
—
|
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: main channel to Port of New York and New Jersey | Statement: [Robbins Reef, nearShippingLane, main channel to Port of New York and New Jersey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearShippingLane Context triple: [Robbins Reef, nearShippingLane, main channel to Port of New York and New Jersey]
-
A.
hasNearbyStreet
Indicates that one entity is located close to or adjacent to a street.
-
B.
nearPass
Indicates that one entity moves or travels close to another entity without necessarily making direct contact or interaction.
-
C.
nearbyStrait
Indicates that one entity is located close to or adjacent to a particular strait.
-
D.
near
chosen
Indicates that one entity is located at a short distance from another entity in space or position.
-
E.
hasApproachRoad
Indicates that one entity is connected to or accessed by another entity via an approach road leading to it.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b982018481908b222df095e318c0 |
completed | March 1, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69a4b741b0cc8190be001a16a81f6d9e |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.