Triple
T22669285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basler Verkehrs-Betriebe |
E559877
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | BVB |
—
|
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: BVB | Statement: [Basler Verkehrs-Betriebe, shortName, BVB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BVB Context triple: [Basler Verkehrs-Betriebe, shortName, BVB]
-
A.
BVB
chosen
BVB is the public transport company that operates much of the tram and bus network in Basel, Switzerland.
-
B.
BVB
BVB is the common abbreviation for Borussia Dortmund, a major professional football club based in Dortmund, Germany.
-
C.
BVB FanWelt
BVB FanWelt is Borussia Dortmund’s official fan and merchandise center, offering supporters a wide range of club products and interactive experiences.
-
D.
Basel BVB
Basel BVB is the main public tram and bus operator in the Swiss city of Basel, providing urban and regional transit services.
-
E.
Frankfurt VGF
Frankfurt VGF is the main public transport operator in Frankfurt am Main, Germany, running the city's tram, metro, and bus services.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1781ed50c8190a6943f51d7337b49 |
completed | April 29, 2026, 3:16 a.m. |
Created at: April 17, 2026, 3:09 p.m.