Triple
T32075991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 79th Street Bridge |
E819150
|
entity |
| Predicate | bayCrossingOf |
P103014
|
FINISHED |
| Object | Biscayne Bay |
—
|
NE NERFINISHED |
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: Biscayne Bay | Statement: [79th Street Bridge, bayCrossingOf, Biscayne Bay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bayCrossingOf Context triple: [79th Street Bridge, bayCrossingOf, Biscayne Bay]
-
A.
crossingOf
Indicates that one entity serves as the intersection or crossing point of two or more linear features, such as roads, paths, or tracks.
-
B.
crossedByRiver
Indicates that a river passes across or through a specified area, feature, or route.
-
C.
waterwayTypeCrossed
Indicates the specific kind of waterway (e.g., river, canal, stream) that is being crossed in the described relationship or action.
-
D.
wasMainRiverCrossingFor
Indicates that one river crossing (such as a bridge, ford, or ferry) served as the primary or most significant crossing point for a particular route, area, or settlement.
-
E.
hasBayCrossing
chosen
Indicates that one place is connected to another by a crossing over a bay, such as a bridge, tunnel, or ferry route.
- 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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b52d33e08190ac04d0a50141d099 |
completed | May 3, 2026, 2:38 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:23 a.m.