Triple
T9890414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heavenly Palace |
E181436
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 天宫 |
E34212
|
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: 天宫 | Statement: [Heavenly Palace, nativeName, 天宫]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 天宫 Context triple: [Heavenly Palace, nativeName, 天宫]
-
A.
Wentian
Wentian is a Chinese space laboratory module that serves as a key component of the Tiangong space station, providing additional research facilities, living space, and support systems for taikonauts in orbit.
-
B.
Mengtian
Mengtian is a Chinese space laboratory module that forms part of the Tiangong space station, supporting scientific experiments and research in orbit.
-
C.
Tiangongyuan station
Tiangongyuan station is a southern terminus station on Beijing's Subway network, serving as a key endpoint for Line 4.
-
D.
Tiangong space station
chosen
The Tiangong space station is China’s modular, permanently crewed orbital outpost that serves as the centerpiece of its independent human spaceflight and research program in low Earth orbit.
-
E.
Yingtian
Yingtian was an important early Ming dynasty capital city, historically centered around present-day Nanjing in China.
- 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_69ca8283a6708190801af7a25a7ebb9f |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cdb47dfa908190884e96e5e5d6f41f |
completed | April 2, 2026, 12:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1eb08075c81908e017df8048daba8 |
completed | April 5, 2026, 4:54 a.m. |
Created at: March 30, 2026, 8:39 p.m.