Triple
T20170536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oroqen |
E491945
|
entity |
| Predicate | relatedEthnicGroups |
P1969
|
FINISHED |
| Object | Hezhen |
—
|
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: Hezhen | Statement: [Oroqen, relatedEthnicGroups, Hezhen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hezhen Context triple: [Oroqen, relatedEthnicGroups, Hezhen]
-
A.
Hezhe
chosen
The Hezhe are a small Tungusic ethnic group in northeastern China, traditionally known for fishing and hunting along the Amur and Ussuri rivers and for their distinctive riverine culture.
-
B.
Zhenjin
Zhenjin was the designated heir and favored son of Kublai Khan, known for his Confucian education and role in the early Yuan dynasty’s administration before his premature death.
-
C.
Henao
Henao is a Spanish-language surname most notably associated with Maria Victoria Henao, the widow of Colombian drug lord Pablo Escobar.
-
D.
Kāihuáng
Kāihuáng is the era name of Emperor Wen of the Sui dynasty, known for a period of major reforms and consolidation in early medieval China.
-
E.
Shenyuan
Shenyuan was the era name used during part of the reign of Emperor Taiwu of the Northern Wei dynasty in early medieval China.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66847ed9481908e6b23b399fa7005 |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.