Triple
T15483923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Müllerstraße |
E376992
|
entity |
| Predicate | hasBusLines |
P39381
|
FINISHED |
| Object | multiple BVG bus routes |
—
|
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: multiple BVG bus routes | Statement: [Müllerstraße, hasBusLines, multiple BVG bus routes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBusLines Context triple: [Müllerstraße, hasBusLines, multiple BVG bus routes]
-
A.
hasBusServices
chosen
Indicates that one location or entity is served by bus routes or bus transportation provided by another.
-
B.
hasTrolleybusLine
Indicates that there exists a trolleybus service or route connecting the related entities.
-
C.
hasBRTLine
Indicates that a bus rapid transit (BRT) line is present, operates on, or serves the referenced entity.
-
D.
hasPublicTransitRoute
Indicates that there exists a public transportation route (such as a bus, train, or tram line) connecting or serving the related entities.
-
E.
hasBusPlatforms
Indicates that a location or facility is equipped with one or more designated platforms for boarding or alighting from buses.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f8e6ff08190b130b3a38f4190e7 |
completed | April 16, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69ded2874b788190999158e0f043be21 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:45 a.m.