Triple
T18339042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhengde Emperor |
E439350
|
entity |
| Predicate | buriedIn |
P196
|
FINISHED |
| Object | Kangling Mausoleum |
—
|
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: Kangling Mausoleum | Statement: [Zhengde Emperor, buriedIn, Kangling Mausoleum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kangling Mausoleum Context triple: [Zhengde Emperor, buriedIn, Kangling Mausoleum]
-
A.
Kangling Mausoleum
chosen
Kangling Mausoleum is the imperial tomb complex in China where the Ming dynasty Zhengde Emperor was interred.
-
B.
Yongkangling Mausoleum
Yongkangling Mausoleum is the imperial tomb complex in China where Emperor Gaozong of the Southern Song dynasty was interred.
-
C.
Yongchang Mausoleum
Yongchang Mausoleum is the imperial tomb complex in China that serves as the final resting place of Emperor Taizu, the founding ruler of the Song dynasty.
-
D.
Dingdongling Mausoleum
Dingdongling Mausoleum is the Qing dynasty imperial tomb complex that serves as the final resting place of Empress Dowager Cixi.
-
E.
Huiling Mausoleum
Huiling Mausoleum is the tomb complex in China where the Tongzhi Emperor of the Qing dynasty is interred.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ed07db48190a15e957c96b1c5bf |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:37 a.m.