Triple
T19117248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line 6 |
E467936
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object |
Bulgwang Station
Bulgwang Station is a subway station in Seoul, South Korea, serving as an interchange stop on the city's metro network.
|
E1452373
|
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: Bulgwang Station | Statement: [Line 6, hasStation, Bulgwang Station]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bulgwang Station Context triple: [Line 6, hasStation, Bulgwang Station]
-
A.
Kwangbok Station
Kwangbok Station is a stop on the Pyongyang Metro system in North Korea, serving passengers along one of the capital’s main underground transit lines.
-
B.
Sangwolgok Station
Sangwolgok Station is a subway station on Seoul’s Line 6 serving the Sangwolgok neighborhood in Seongbuk-gu, South Korea.
-
C.
Kwangmyong Station
Kwangmyong Station is a stop on the Pyongyang Metro system in North Korea’s capital city.
-
D.
Cheonggu Station
Cheonggu Station is a subway station on Seoul’s extensive metropolitan rail network, serving passengers on Line 6.
-
E.
Danggogae Station
Danggogae Station is a subway station in northeastern Seoul, South Korea, serving as the northern terminus of Seoul Subway Line 4.
- 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: Bulgwang Station Triple: [Line 6, hasStation, Bulgwang Station]
Generated description
Bulgwang Station is a subway station in Seoul, South Korea, serving as an interchange stop on the city's metro network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bulgwang Station Target entity description: Bulgwang Station is a subway station in Seoul, South Korea, serving as an interchange stop on the city's metro network.
-
A.
Kwangbok Station
Kwangbok Station is a stop on the Pyongyang Metro system in North Korea, serving passengers along one of the capital’s main underground transit lines.
-
B.
Sangwolgok Station
Sangwolgok Station is a subway station on Seoul’s Line 6 serving the Sangwolgok neighborhood in Seongbuk-gu, South Korea.
-
C.
Kwangmyong Station
Kwangmyong Station is a stop on the Pyongyang Metro system in North Korea’s capital city.
-
D.
Cheonggu Station
Cheonggu Station is a subway station on Seoul’s extensive metropolitan rail network, serving passengers on Line 6.
-
E.
Danggogae Station
Danggogae Station is a subway station in northeastern Seoul, South Korea, serving as the northern terminus of Seoul Subway Line 4.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e399a6d8819090a9501ff1637b9d |
completed | April 20, 2026, 8:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0900574d988190bd635ebb22c54357 |
completed | May 16, 2026, 11:40 p.m. |
| NEDg | Description generation | batch_6a0901a0dac081909f9184e99a70419a |
completed | May 16, 2026, 11:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09023cf27081908eb246367215ae12 |
completed | May 16, 2026, 11:48 p.m. |
Created at: April 10, 2026, 12:05 p.m.