Triple
T17709761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sviatoshynsko–Brovarska line |
E441531
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object |
Vokzalna
Vokzalna is a Kyiv Metro station on the Sviatoshynsko–Brovarska line that serves the city’s main railway terminal.
|
E1284033
|
NE FINISHED |
How this triple was built (4 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: Vokzalna | Statement: [Sviatoshynsko–Brovarska line, hasStation, Vokzalna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vokzalna Context triple: [Sviatoshynsko–Brovarska line, hasStation, Vokzalna]
-
A.
Novza station
Novza station is a metro station on the Tashkent Metro system in Tashkent, Uzbekistan.
-
B.
Opatov station
Opatov station is a Prague Metro station on Line C serving the Opatov district in the southern part of the city.
-
C.
Vác
Vác is a historic town on the Danube in northern Hungary, known for its Baroque architecture and role as a regional cultural and religious center.
-
D.
Villach railway junction
Villach railway junction is a major Austrian rail hub in the city of Villach, serving as a key crossroads for national and international train connections in the state of Carinthia.
-
E.
Vajna
Vajna is the surname of Andrew G. Vajna, a prominent Hungarian-American film producer known for co-founding Carolco Pictures and producing major action films such as the Rambo series.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Vokzalna Triple: [Sviatoshynsko–Brovarska line, hasStation, Vokzalna]
Generated description
Vokzalna is a Kyiv Metro station on the Sviatoshynsko–Brovarska line that serves the city’s main railway terminal.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vokzalna Target entity description: Vokzalna is a Kyiv Metro station on the Sviatoshynsko–Brovarska line that serves the city’s main railway terminal.
-
A.
Novza station
Novza station is a metro station on the Tashkent Metro system in Tashkent, Uzbekistan.
-
B.
Opatov station
Opatov station is a Prague Metro station on Line C serving the Opatov district in the southern part of the city.
-
C.
Vác
Vác is a historic town on the Danube in northern Hungary, known for its Baroque architecture and role as a regional cultural and religious center.
-
D.
Villach railway junction
Villach railway junction is a major Austrian rail hub in the city of Villach, serving as a key crossroads for national and international train connections in the state of Carinthia.
-
E.
Vajna
Vajna is the surname of Andrew G. Vajna, a prominent Hungarian-American film producer known for co-founding Carolco Pictures and producing major action films such as the Rambo series.
- F. None of above. chosen
Provenance (5 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_69d8b9ea20b48190ace88bb46b01e6a9 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4729a9a9c81908d65ff0bda12c961 |
completed | April 19, 2026, 6:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a023025ae808190ba3e9a875bfc68e9 |
completed | May 11, 2026, 7:38 p.m. |
| NEDg | Description generation | batch_6a023249cfb0819091d3fa8c3089f241 |
completed | May 11, 2026, 7:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0232ce696c81908d0e57ea214f88ce |
completed | May 11, 2026, 7:49 p.m. |
Created at: April 10, 2026, 10:05 a.m.