Triple
T37947498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Eustis |
E946645
|
entity |
| Predicate | isNavigableWith |
P20520
|
FINISHED |
| Object | recreational boats |
—
|
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: recreational boats | Statement: [Lake Eustis, isNavigableWith, recreational boats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isNavigableWith Context triple: [Lake Eustis, isNavigableWith, recreational boats]
-
A.
isNavigableVia
Indicates that one entity can be reached, traversed, or accessed by means of another entity (such as a route, medium, or pathway).
-
B.
isNavigableNear
Indicates that an entity can be traversed or passed through in close proximity to another specified entity or location.
-
C.
navigableFor
chosen
Indicates that one entity (such as a path, route, or medium) can be traversed or used for movement by another entity (such as a vehicle, vessel, or agent).
-
D.
navigableFrom
Indicates that one location or entity can be reached or traversed from another, typically via a valid path, route, or connection.
-
E.
navigableTo
Indicates that one entity can be reached or traversed to from another entity, typically following valid paths or connections within a system or environment.
- 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_69f76ef64cf08190ad3e1114b62aac67 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc7b78f9481909f4f8fc2e3fdcde1 |
completed | May 6, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69fbbd18c9908190928d274f8731dfa8 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:20 p.m.