Triple
T5036775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco (via ferry and bus connections) |
E113443
|
entity |
| Predicate | connectionMode |
P51916
|
FINISHED |
| Object | ferry |
—
|
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: ferry | Statement: [San Francisco (via ferry and bus connections), connectionMode, ferry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectionMode Context triple: [San Francisco (via ferry and bus connections), connectionMode, ferry]
-
A.
connectionEstablishmentMethod
Indicates the method or mechanism by which a connection between entities is initiated or established.
-
B.
connectsWithMode
chosen
Indicates a relationship where one entity connects to another using a specified method, channel, or mode of connection.
-
C.
communicationMode
Indicates the method or channel through which communication between entities is carried out.
-
D.
connectionTo
Indicates a relationship in which one entity is linked, associated, or otherwise related to another entity.
-
E.
connectsState
Indicates a relationship where one entity serves as a link or conduit between different states, conditions, or statuses of another 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_69bd44384298819089c49e7c330ec7b8 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73bb069c8190af86f1b2f95f3d95 |
completed | March 20, 2026, 4:20 p.m. |
| PD | Predicate disambiguation | batch_69bd71529d608190a53470ba6c14bb1d |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:37 p.m.