Triple
T14677186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dongsha Islands |
E344675
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 東沙群島 |
E344675
|
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: 東沙群島 | Statement: [Dongsha Islands, nativeName, 東沙群島]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 東沙群島 Context triple: [Dongsha Islands, nativeName, 東沙群島]
-
A.
東沙環礁
東沙環礁是位於南海北部、由中華民國實際管轄的珊瑚環礁與島礁群，因其豐富的海洋生態與戰略位置而備受關注。
-
B.
釣魚臺列嶼
釣魚臺列嶼是位於東海、由中日台多方主權主張的無人島群，以其豐富漁場與潛在油氣資源而備受關注。
-
C.
Dongsha Islands
chosen
The Dongsha Islands, also known as the Pratas Islands, are a small, strategically located group of coral islands and atolls in the northern South China Sea administered by Taiwan.
-
D.
Lanyu
Lanyu is a small volcanic island off Taiwan’s southeastern coast, known for its indigenous Tao (Yami) culture, lush landscapes, and rich marine biodiversity.
-
E.
Penghu Islands
The Penghu Islands are an archipelago in the Taiwan Strait known for their volcanic landscapes, historic temples, traditional fishing culture, and popular beach and water-sport tourism.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb567c2b88190a9639e61b6fba7df |
completed | April 14, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde17e5a1c8190b1bf5565eab9d519 |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:27 a.m.