Triple
T19927119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akhmeteli–Varketili Line |
E478952
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object |
Samgori station
Samgori station is a metro station on the Tbilisi Metro system in Tbilisi, Georgia.
|
E1409991
|
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: Samgori station | Statement: [Akhmeteli–Varketili Line, hasStation, Samgori station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Samgori station Context triple: [Akhmeteli–Varketili Line, hasStation, Samgori station]
-
A.
Sadang Station
Sadang Station is a major Seoul Metropolitan Subway transfer station in southern Seoul, serving as an important transit hub for commuters in and around Gwanak-gu.
-
B.
Asan Station
Asan Station is a railway station in Asan, South Korea, serving as a regional transit hub connecting local and intercity rail services.
-
C.
Yeouinaru Station
Yeouinaru Station is a subway station on Seoul Subway Line 5 located in the Yeouido district of Seoul, South Korea, serving the Han River riverside area and nearby business complexes.
-
D.
Sajik Station
Sajik Station is a subway station in Busan, South Korea, serving the Dongnae District on the Busan Metro network.
-
E.
Geombawi Station
Geombawi Station is a railway station on South Korea's Airport Railroad Express (AREX) line serving the Incheon area.
- 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: Samgori station Triple: [Akhmeteli–Varketili Line, hasStation, Samgori station]
Generated description
Samgori station is a metro station on the Tbilisi Metro system in Tbilisi, Georgia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Samgori station Target entity description: Samgori station is a metro station on the Tbilisi Metro system in Tbilisi, Georgia.
-
A.
Sadang Station
Sadang Station is a major Seoul Metropolitan Subway transfer station in southern Seoul, serving as an important transit hub for commuters in and around Gwanak-gu.
-
B.
Asan Station
Asan Station is a railway station in Asan, South Korea, serving as a regional transit hub connecting local and intercity rail services.
-
C.
Yeouinaru Station
Yeouinaru Station is a subway station on Seoul Subway Line 5 located in the Yeouido district of Seoul, South Korea, serving the Han River riverside area and nearby business complexes.
-
D.
Sajik Station
Sajik Station is a subway station in Busan, South Korea, serving the Dongnae District on the Busan Metro network.
-
E.
Geombawi Station
Geombawi Station is a railway station on South Korea's Airport Railroad Express (AREX) line serving the Incheon area.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659ca52c881908dc8053bf61be4c4 |
completed | April 20, 2026, 4:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a081f2428d88190bd5aaad3c005779b |
completed | May 16, 2026, 7:39 a.m. |
| NEDg | Description generation | batch_6a08203132d48190b3f1313dae3e6fc1 |
completed | May 16, 2026, 7:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0821390af08190a4aca33d33f0e71d |
completed | May 16, 2026, 7:48 a.m. |
Created at: April 10, 2026, 1:53 p.m.