Triple
T4998752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metro line 50 |
E112313
|
entity |
| Predicate | operatedBy |
P86
|
FINISHED |
| Object | GVB |
E28406
|
NE 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: GVB | Statement: [Metro line 50, operatedBy, GVB]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GVB Context triple: [Metro line 50, operatedBy, GVB]
-
A.
GVB
chosen
GVB is Amsterdam’s primary public transport company, operating the city’s trams, buses, metro, and ferries.
-
B.
VBB
VBB is the public transport authority and fare network that coordinates and integrates regional and urban transit services across Berlin and the surrounding Brandenburg region.
-
C.
GVA
GVA is the IATA airport code for Geneva Airport, the international airport serving Geneva, Switzerland and the surrounding region.
-
D.
VBG
VBG is the abbreviated name of the German association of botanical gardens, Verband Botanischer Gärten e.V.
-
E.
BVG
BVG is Berlin’s main public transport company, operating the city’s U-Bahn, trams, buses, and ferries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd72ba2e588190bfd76beda0c4105c |
completed | March 20, 2026, 4:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be8a38484881909893e5450dc33265 |
completed | March 21, 2026, 12:08 p.m. |
Created at: March 20, 2026, 1:34 p.m.