Triple
T9501571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Xianzong of Tang |
E229152
|
entity |
| Predicate | eraName |
P2938
|
FINISHED |
| Object | Yuanhe |
E803565
|
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: Yuanhe | Statement: [Emperor Xianzong of Tang, eraName, Yuanhe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yuanhe Context triple: [Emperor Xianzong of Tang, eraName, Yuanhe]
-
A.
Yuanhe
chosen
Yuanhe was the era name used during the reign of Emperor Xianzong in the Tang dynasty, marking a specific period in Chinese imperial history.
-
B.
Kaiyuan
Kaiyuan is a county-level city in Honghe Hani and Yi Autonomous Prefecture in Yunnan Province, southwestern China.
-
C.
Yongyuan
Yongyuan was the era name used during part of Emperor Zhang's rule in the Eastern Han dynasty of ancient China.
-
D.
Longcheng
Longcheng was the principal royal city and political center of the Xiongnu confederation in ancient Inner Asia.
-
E.
Yuanhe era
The Yuanhe era was a regnal period in the early 9th century during the Tang dynasty, marked by Emperor Xianzong’s efforts to reassert central imperial authority over powerful regional warlords.
- 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_69ca84753660819098e8d416e89e26ae |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd983d4b708190a4dfef1246986a26 |
completed | April 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d14c02de448190a2feea16d5461726 |
completed | April 4, 2026, 5:36 p.m. |
Created at: March 30, 2026, 7:57 p.m.