Triple
T882364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yerba Buena Island |
E19053
|
entity |
| Predicate | hasRoadAccessVia |
P4067
|
FINISHED |
| Object | Bay Bridge on-ramps and off-ramps |
—
|
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: Bay Bridge on-ramps and off-ramps | Statement: [Yerba Buena Island, hasRoadAccessVia, Bay Bridge on-ramps and off-ramps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoadAccessVia Context triple: [Yerba Buena Island, hasRoadAccessVia, Bay Bridge on-ramps and off-ramps]
-
A.
roadAccessVia
Indicates that one location or area is reachable from another specifically by using a particular road or road segment.
-
B.
hasApproachRoad
chosen
Indicates that one entity is connected to or accessed by another entity via an approach road leading to it.
-
C.
connectsToHighway
Indicates that one location, road, or route has a direct access point or linkage to a highway.
-
D.
linkedByRoadTo
Indicates that two locations are directly connected to each other by a road suitable for travel.
-
E.
roadServed
Indicates that a road is provided with necessary services or infrastructure support by a responsible entity.
- 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_69a4939c32488190a7ccd41cf0abb22b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4accc863c8190be9e5350732c30b1 |
completed | March 1, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69a4aa8eca748190b58e0f08b30fba43 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.