Triple
T14368012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Budapest Metro Line 2 |
E356284
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | BKV |
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 | Statement: [Budapest Metro Line 2, operator, BKV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BKV Context triple: [Budapest Metro Line 2, operator, BKV]
-
A.
BKV
chosen
BKV is the main public transportation company of Budapest, Hungary, responsible for operating the city’s metro, trams, buses, and trolleybuses.
-
B.
KBV
KBV is the IATA airport code for Krabi International Airport, a major gateway to Thailand’s Krabi province and nearby Andaman Sea destinations.
-
C.
BKL
BKL is an alternative name for the Big Circle Line, a major circular metro line in Moscow’s rapid transit system.
-
D.
BKL
BKL is the FAA airport code for Burke Lakefront Airport, a public airport located on the shore of Lake Erie in Cleveland, Ohio.
-
E.
BKB
BKB is the IATA airport code for Nal Airport, a regional airport serving Bikaner in the Indian state of Rajasthan.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8faf00e8819087d7100e9d8c1877 |
completed | April 14, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c51bf888190b1776461884c4514 |
completed | May 8, 2026, 2:37 a.m. |
Created at: April 10, 2026, 1:15 a.m.