Triple
T4783892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shangchuan Island |
E106429
|
entity |
| Predicate | locatedOffCoastOf |
P212
|
FINISHED |
| Object | Taishan |
E468895
|
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: Taishan | Statement: [Shangchuan Island, locatedOffCoastOf, Taishan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taishan Context triple: [Shangchuan Island, locatedOffCoastOf, Taishan]
-
A.
Taishan
chosen
Taishan is a county-level city in Guangdong Province, China, known as the ancestral homeland of many overseas Chinese and for its coastal scenery and historic villages.
-
B.
Mount Tai
Mount Tai is one of China’s most famous and historically significant sacred mountains, revered in Chinese religion and culture for millennia.
-
C.
Tanluan
Tanluan was a pioneering Chinese Buddhist monk and philosopher whose teachings helped systematize and popularize Pure Land Buddhism in East Asia.
-
D.
Tianzhu Peak
Tianzhu Peak is the tallest summit of China’s Wudang Mountains, a range famed for its Taoist temples and martial arts heritage.
-
E.
Mount Zao
Mount Zao is a prominent volcanic mountain range in northern Japan known for its ski resorts, hot springs, and the emerald-colored Okama crater lake.
- 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_69bd43f4a9588190bf73e20bc27c03cc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd65ad3a188190872e47e3a3bf504b |
completed | March 20, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be4d93f2cc8190acf96766d2c5a946 |
completed | March 21, 2026, 7:49 a.m. |
Created at: March 20, 2026, 1:22 p.m.