Triple
T19881445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gyeongchun Line |
E477782
|
entity |
| Predicate | hasService |
P182
|
FINISHED |
| Object | ITX-Cheongchun |
—
|
NE NERFINISHED |
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: ITX-Cheongchun | Statement: [Gyeongchun Line, hasService, ITX-Cheongchun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ITX-Cheongchun Context triple: [Gyeongchun Line, hasService, ITX-Cheongchun]
-
A.
ITX-Cheongchun
chosen
ITX-Cheongchun is a South Korean intercity express train service connecting Seoul with major regional cities, designed to offer faster and more comfortable travel for young and general passengers alike.
-
B.
ITX-Saemaeul
ITX-Saemaeul is a class of South Korean intercity express trains operated by Korail, offering faster and more comfortable service than conventional trains on major routes.
-
C.
KTX-Eum
KTX-Eum is a South Korean high-speed electric multiple unit train operated by Korail, designed for intercity services on the country’s high-speed rail network.
-
D.
KTX
KTX is South Korea’s high-speed rail service that connects major cities such as Seoul and Busan.
-
E.
KTX
KTX is a Khronos Group-defined container format for efficiently storing and transmitting GPU-ready texture data in graphics applications.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658df3f5c81909b5b290de91b8d50 |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.