Triple
T2973866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spuyten Duyvil Bridge |
E80346
|
entity |
| Predicate | opensFor |
P4864
|
FINISHED |
| Object | marine traffic |
—
|
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: marine traffic | Statement: [Spuyten Duyvil Bridge, opensFor, marine traffic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opensFor Context triple: [Spuyten Duyvil Bridge, opensFor, marine traffic]
-
A.
openedForUse
Indicates that something has been made accessible and available for its intended operation or use.
-
B.
openedForCurrentUse
Indicates that an entity has been opened and is currently available for its intended use or operation.
-
C.
opens
chosen
Indicates that one entity causes or allows another entity (such as an object, space, or resource) to become accessible or no longer closed.
-
D.
openedForPublic
Indicates that something has been made accessible or available for use, entry, or participation by the general public.
-
E.
openedForEvent
Indicates that a venue or location is made accessible and operational specifically for a particular event.
- 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_69ad8b14ffe881908ffed62f9595c867 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9987bb6c8190adfb447b76276962 |
completed | March 8, 2026, 3:45 p.m. |
| PD | Predicate disambiguation | batch_69ad96105a708190a9ec4838cbcb1207 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:58 p.m.