Triple
T28794938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dong Dang–Pingxiang rail link to China |
E727059
|
entity |
| Predicate | terminusInVietnam |
P388
|
FINISHED |
| Object | Dong Dang railway station |
E1834138
|
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: Dong Dang railway station | Statement: [Dong Dang–Pingxiang rail link to China, terminusInVietnam, Dong Dang railway station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terminusInVietnam Context triple: [Dong Dang–Pingxiang rail link to China, terminusInVietnam, Dong Dang railway station]
-
A.
terminus
chosen
Indicates that one entity serves as the final endpoint or stopping place for another entity’s movement, route, or process.
-
B.
terminusInland
Indicates that something ends, concludes, or has its final point within an inland area rather than at a coast or shoreline.
-
C.
terminusTowards
Indicates that one entity serves as the endpoint or directional terminus oriented toward another entity.
-
D.
terminusNorth
Indicates that one entity serves as the northern endpoint or final stop of another entity, such as a route, line, or path.
-
E.
terminusSouthCountry
Indicates that the southern terminus of a route, line, or connection is located within the specified country.
- F. None of above.
Provenance (4 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_69f0319b7c44819085736bcc256185e6 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a24d3ebf40881908d0f7bbedb62f137 |
completed | June 7, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69f69d17e8d48190b30bcc2f4bd81eb2 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 28, 2026, 6:24 a.m.