Triple
T9719309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guilin |
E235421
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Yangshuo |
E816967
|
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: Yangshuo | Statement: [Guilin, near, Yangshuo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yangshuo Context triple: [Guilin, near, Yangshuo]
-
A.
Guilin
Guilin is a scenic city in southern China’s Guangxi region, famed for its dramatic karst mountains and picturesque Li River landscapes.
-
B.
Yangshuo County
chosen
Yangshuo County is a scenic county in southern China famed for its dramatic karst mountains, Li River landscapes, and popularity as a tourist and rock-climbing destination.
-
C.
Wuzhou
Wuzhou is a prefecture-level city in eastern Guangxi, China, known as a regional transport hub and commercial center along the Xi River.
-
D.
Langting
Langting is a small town in the Dima Hasao (formerly North Cachar Hills) district of Assam, India, known as a local administrative and transport hub in the hilly region.
-
E.
Nanning
Nanning is the capital and largest city of China’s Guangxi Zhuang Autonomous Region, known as a key economic hub and “Green City” in the Lingnan cultural area.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca84d0123c819096f9dc3b6abb0881 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e4022c4819097455f14dd9b1a77 |
completed | April 1, 2026, 10:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1afa6d0d08190a8008b675c9aabb1 |
completed | April 5, 2026, 12:41 a.m. |
Created at: March 30, 2026, 8:20 p.m.