Triple
T22780496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaoshan people |
E563822
|
entity |
| Predicate | ChineseName |
P744
|
FINISHED |
| Object | 高山族 |
—
|
NE NERFINISHED |
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: 高山族 | Statement: [Gaoshan people, ChineseName, 高山族]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 高山族 Context triple: [Gaoshan people, ChineseName, 高山族]
-
A.
畲族
畲族是中国南方主要分布于福建、浙江、江西、广东等地、以畲语和汉语为主要语言、拥有独特山歌、婚俗和服饰文化的少数民族。
-
B.
Gaoshan people
chosen
The Gaoshan people are an officially recognized ethnic group in China historically referring to various indigenous Austronesian-speaking peoples of Taiwan.
-
C.
Atayal people
The Atayal people are one of Taiwan’s major indigenous Austronesian groups, known for their facial tattoo traditions, weaving, and distinct language and culture concentrated in the island’s northern and central mountain regions.
-
D.
客家人
客家人是主要分布于中国南方及世界各地、以客家话和独特客家文化著称的汉族民系。
-
E.
Rukai people
The Rukai people are one of Taiwan’s indigenous Austronesian groups, known for their rich oral traditions, distinctive slate houses, and intricate social and ritual customs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c2cab0881908df1d0629b43d350 |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 3:28 p.m.