Triple
T15551417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Budapest tram network |
E370752
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | BKV Zrt. |
E349652
|
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: BKV Zrt. | Statement: [Budapest tram network, operator, BKV Zrt.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BKV Zrt. Context triple: [Budapest tram network, operator, BKV Zrt.]
-
A.
MVK Zrt.
MVK Zrt. is the municipal public transport company operating bus and tram services in the city of Miskolc, Hungary.
-
B.
BGYH Zrt.
BGYH Zrt. is a Budapest-based company that operates and manages the city’s historic thermal baths and spa facilities.
-
C.
BKV
chosen
BKV is the main public transportation company of Budapest, Hungary, responsible for operating the city’s metro, trams, buses, and trolleybuses.
-
D.
BVZ Holding
BVZ Holding is a Swiss transport and tourism company that operates and manages regional railways and related services in the Alpine region.
-
E.
BZV
BZV is the IATA airport code for Maya-Maya Airport, the main international airport serving Brazzaville in the Republic of the Congo.
- 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_69d85cc6cf40819091f4a5facee1ebe6 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04a9551288190a583e8291c35f521 |
completed | April 16, 2026, 2:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4560008c81908ebd278c3dc45045 |
completed | May 9, 2026, 2:32 p.m. |
Created at: April 10, 2026, 4:08 a.m.