Triple
T24764619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Block Island Express |
E619545
|
entity |
| Predicate | bodyOfWaterTraversed |
P111166
|
FINISHED |
| Object | Long Island Sound |
E17706
|
NE 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: Long Island Sound | Statement: [Block Island Express, bodyOfWaterTraversed, Long Island Sound]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyOfWaterTraversed Context triple: [Block Island Express, bodyOfWaterTraversed, Long Island Sound]
-
A.
navigatesWaterBody
chosen
Indicates that an entity moves through or across a body of water as a means of travel or operation.
-
B.
waterbodyOnCourse
Indicates that a waterbody lies along, intersects, or is situated on the path of a particular course, such as a river or stream.
-
C.
lakeTypeCrossed
Indicates that one entity has traversed or passed across a lake of a specified type.
-
D.
crossesWaterBody
Indicates that an entity moves from one side of a water body to the other by passing over, through, or across it.
-
E.
visitedBodyOfWater
Indicates that an entity has gone to and been physically present at a particular body of water.
- F. None of above.
Provenance (4 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_69e2fabbea94819092ed41348909622f |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f410a4591c81909f918efd84a1f6f6 |
completed | May 1, 2026, 2:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a10c10760a4819089c46eae89f764cd |
completed | May 22, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69f40ef612c88190ab2f3f08d4a92018 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 4:28 a.m.