Triple
T1626168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cui Hao |
E35148
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | 黃鶴樓 |
E5775
|
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: 黃鶴樓 | Statement: [Cui Hao, notableWork, 黃鶴樓]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 黃鶴樓 Context triple: [Cui Hao, notableWork, 黃鶴樓]
-
A.
Yellow Crane Tower
chosen
Yellow Crane Tower is a historic and iconic Chinese pavilion in Wuhan, renowned for its classical architecture, cultural significance, and scenic views over the Yangtze River.
-
B.
Wenchang Tower
Wenchang Tower is a historic pavilion within Beijing’s Summer Palace complex, known for its traditional Chinese architectural style and scenic lakeside setting.
-
C.
Huairen Hall
Huairen Hall is a prominent building within Beijing’s Zhongnanhai leadership compound, historically used for important government meetings and state activities.
-
D.
Longshan Temple
Longshan Temple is a historic and richly decorated Buddhist and folk religion temple in Taipei, Taiwan, renowned as one of the city’s most important religious and cultural sites.
-
E.
Yuelu Mountain
Yuelu Mountain is a scenic and historic mountain area in Changsha, China, known for its ancient academy, temples, and natural landscapes.
- 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_69a886023194819080a3fccd6e325d0e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a909d2fbe881908451ecd363cc33b0 |
completed | March 5, 2026, 4:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad58d12e808190a1319b1c87bcd22e |
completed | March 8, 2026, 11:09 a.m. |
Created at: March 4, 2026, 7:28 p.m.