Triple
T20912885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alaskan Way Viaduct |
E514992
|
entity |
| Predicate | tunnelLocation |
P141661
|
FINISHED |
| Object | beneath downtown Seattle |
—
|
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: beneath downtown Seattle | Statement: [Alaskan Way Viaduct, tunnelLocation, beneath downtown Seattle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tunnelLocation Context triple: [Alaskan Way Viaduct, tunnelLocation, beneath downtown Seattle]
-
A.
tunnelType
Indicates the specific kind or classification of a tunnel associated with an entity.
-
B.
tunnelName
Indicates the name assigned to a specific tunnel in the relationship or data model.
-
C.
partOfTunnel
Indicates that one entity forms a physical segment or component within the structure or extent of a tunnel.
-
D.
usesTunnel
Indicates that one entity makes use of a tunnel as a passage or route to reach or connect to another entity.
-
E.
connectionLocation
Indicates the place or spatial context where a connection between entities occurs or is established.
- F. None of above. chosen
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_69e0b4f9d5ec8190bb2bd27350ed341c |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6ec60d3288190897a087bbdd4f005 |
completed | April 21, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c9ac91108190a6700fcdf2f11890 |
completed | April 20, 2026, 6:37 a.m. |
| PDg | Predicate description generation | batch_69e5d53d22d08190bc17ed4bed53804a |
completed | April 20, 2026, 7:26 a.m. |
Created at: April 16, 2026, 12:48 p.m.