Triple
T14069616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tengwang Pavilion |
E338569
|
entity |
| Predicate | originalBuilderTitle |
P3052
|
FINISHED |
| Object |
Prince Teng
Prince Teng was a Tang dynasty imperial prince best known for lending his name to the famed Tengwang Pavilion, one of China's most celebrated historic towers.
|
E1078064
|
NE FINISHED |
How this triple was built (5 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: Prince Teng | Statement: [Tengwang Pavilion, originalBuilderTitle, Prince Teng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prince Teng Context triple: [Tengwang Pavilion, originalBuilderTitle, Prince Teng]
-
A.
Prince Chui
Prince Chui was a royal prince of the Thonburi Kingdom and a son of King Taksin of Siam.
-
B.
Prince Dan of Yan
Prince Dan of Yan was a royal prince of the ancient Chinese state of Yan, best known for orchestrating the failed assassination attempt on the Qin king by the assassin Jing Ke during the Warring States period.
-
C.
Prince of Jin
Prince of Jin was the princely title held by Zhao Guangyi before he ascended the throne as Emperor Taizong of the Song dynasty.
-
D.
Prince of Jin
The Prince of Jin was a noble title held by Li Zhi before he became Emperor Gaozong of the Tang dynasty in China.
-
E.
Prince Toneri
Prince Toneri was an 8th-century Japanese imperial prince and scholar best known for overseeing the compilation of the historical chronicle Nihon Shoki.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Prince Teng Triple: [Tengwang Pavilion, originalBuilderTitle, Prince Teng]
Generated description
Prince Teng was a Tang dynasty imperial prince best known for lending his name to the famed Tengwang Pavilion, one of China's most celebrated historic towers.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Prince Teng Target entity description: Prince Teng was a Tang dynasty imperial prince best known for lending his name to the famed Tengwang Pavilion, one of China's most celebrated historic towers.
-
A.
Prince Chui
Prince Chui was a royal prince of the Thonburi Kingdom and a son of King Taksin of Siam.
-
B.
Prince Dan of Yan
Prince Dan of Yan was a royal prince of the ancient Chinese state of Yan, best known for orchestrating the failed assassination attempt on the Qin king by the assassin Jing Ke during the Warring States period.
-
C.
Prince of Jin
Prince of Jin was the princely title held by Zhao Guangyi before he ascended the throne as Emperor Taizong of the Song dynasty.
-
D.
Prince of Jin
The Prince of Jin was a noble title held by Li Zhi before he became Emperor Gaozong of the Tang dynasty in China.
-
E.
Prince Toneri
Prince Toneri was an 8th-century Japanese imperial prince and scholar best known for overseeing the compilation of the historical chronicle Nihon Shoki.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalBuilderTitle Context triple: [Tengwang Pavilion, originalBuilderTitle, Prince Teng]
-
A.
builderTitle
chosen
Indicates the formal title or designation held by a person or entity in their role as a builder.
-
B.
createdTitleBy
Indicates that a title (such as a work, document, or creative piece) was created by a specific agent or creator.
-
C.
originallyTitleOf
Indicates that one title is the original title from which another work, edition, or localized title is derived.
-
D.
originalTitleOfWork
Indicates that one work is the original title under which another work was first created, published, or released.
-
E.
originalTitleName
Indicates that one entity is the original or primary title name associated with another entity.
- F. None of above.
Provenance (6 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de568d0404819087e0fe37c72162cb |
completed | April 14, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb66cfe2c8190af8354316d4f4df9 |
completed | May 7, 2026, 3:57 p.m. |
| NEDg | Description generation | batch_69fcc5c893dc81908538136e0f9170ca |
completed | May 7, 2026, 5:03 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fcc64ac93c8190ad40a04c74f70e18 |
completed | May 7, 2026, 5:05 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.