Triple
T16658725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xiangshan MRT Station |
E404801
|
entity |
| Predicate | hasRomanizedName |
P2508
|
FINISHED |
| Object | Xiangshan |
E404800
|
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: Xiangshan | Statement: [Xiangshan MRT Station, hasRomanizedName, Xiangshan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xiangshan Context triple: [Xiangshan MRT Station, hasRomanizedName, Xiangshan]
-
A.
Xiangshan
Xiangshan is a mountain in Luoyang, China, known for overlooking the Longmen Grottoes and associated with historic temples and scenic landscapes.
-
B.
Xiangshan
Xiangshan was the historical name of the city now known as Zhongshan in Guangdong Province, China, an area notable for being the birthplace of Sun Yat-sen.
-
C.
Xiàngshān
chosen
Xiàngshān is a popular hiking spot in Taipei, Taiwan, known for its scenic trails and panoramic views of the city and Taipei 101.
-
D.
Songshan
Songshan is one of China's Five Great Mountains, renowned as a sacred Taoist and Buddhist site and home to the historic Shaolin Monastery.
-
E.
Songshan
Songshan is a district in eastern Taipei, Taiwan, known for its busy transportation hubs, night markets, and mix of commercial and residential areas.
- 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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37bfcbb6881909c0419174dd017dc |
completed | April 18, 2026, 12:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a008a30e55c8190a5047656b9873a0e |
completed | May 10, 2026, 1:37 p.m. |
Created at: April 10, 2026, 5:18 a.m.