Triple
T19298368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhurong rover |
E482626
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Zhurong |
—
|
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: Zhurong | Statement: [Zhurong rover, namedAfter, Zhurong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zhurong Context triple: [Zhurong rover, namedAfter, Zhurong]
-
A.
Zhurong
chosen
Zhurong is China’s first Mars rover, part of the Tianwen-1 mission, designed to explore the Martian surface and study its geology and climate.
-
B.
Zhurong (fire deity)
Zhurong is an ancient Chinese fire deity and mythological figure often regarded as a god of fire and the south in early Chinese cosmology.
-
C.
Houzhao
Houzhao is the given name of Zhu Houzhao, the Ming dynasty emperor known posthumously as the Zhengde Emperor.
-
D.
Tian Wen
Tian Wen is an ancient Chinese poetic work traditionally attributed to Qu Yuan, known for its rich mythological imagery and philosophical questioning.
-
E.
Zhurong Gong (Zhurong Temple)
Zhurong Gong (Zhurong Temple) is an ancient Chinese temple dedicated to the fire god Zhurong, located on Mount Heng in Hunan Province.
- 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_69d8e8cf61b0819096fe3e4107827c4e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fc86f8648190920d122bb141c6e5 |
completed | April 20, 2026, 10:14 a.m. |
Created at: April 10, 2026, 1:31 p.m.