Triple
T616364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taipei |
E14412
|
entity |
| Predicate | isSeatOf |
P62
|
FINISHED |
| Object |
Control Yuan
The Control Yuan is one of the five branches of government in the Republic of China (Taiwan), responsible for oversight, auditing, and impeachment of public officials.
|
E77111
|
NE FINISHED |
How this triple was built (4 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: Control Yuan | Statement: [Taipei, isSeatOf, Control Yuan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Control Yuan Context triple: [Taipei, isSeatOf, Control Yuan]
-
A.
Wu
Wu is a common Chinese surname borne by many notable individuals across politics, academia, entertainment, and sports.
-
B.
Pei
Pei is the family name of I. M. Pei, the renowned Chinese-American architect known for designing landmarks such as the Louvre Pyramid in Paris.
-
C.
Xuan
Xuan is a Vietnamese surname commonly used as a family name in Vietnam.
-
D.
Kun Huang
Kun Huang was a prominent Chinese physicist and crystallographer known for his influential work in solid-state physics and lattice dynamics.
-
E.
Cai Hesen
Cai Hesen was a prominent early Chinese Communist theorist and revolutionary leader who played a key role in shaping the ideological foundations of the Chinese Communist Party.
- 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: Control Yuan Triple: [Taipei, isSeatOf, Control Yuan]
Generated description
The Control Yuan is one of the five branches of government in the Republic of China (Taiwan), responsible for oversight, auditing, and impeachment of public officials.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Control Yuan Target entity description: The Control Yuan is one of the five branches of government in the Republic of China (Taiwan), responsible for oversight, auditing, and impeachment of public officials.
-
A.
Wu
Wu is a common Chinese surname borne by many notable individuals across politics, academia, entertainment, and sports.
-
B.
Pei
Pei is the family name of I. M. Pei, the renowned Chinese-American architect known for designing landmarks such as the Louvre Pyramid in Paris.
-
C.
Xuan
Xuan is a Vietnamese surname commonly used as a family name in Vietnam.
-
D.
Kun Huang
Kun Huang was a prominent Chinese physicist and crystallographer known for his influential work in solid-state physics and lattice dynamics.
-
E.
Cai Hesen
Cai Hesen was a prominent early Chinese Communist theorist and revolutionary leader who played a key role in shaping the ideological foundations of the Chinese Communist Party.
- F. None of above. chosen
Provenance (5 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e22f3688190a512bec3f0347814 |
completed | March 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5554b4f888190b9b64ece37087bf4 |
completed | March 2, 2026, 9:15 a.m. |
| NEDg | Description generation | batch_69a555ae08b88190aad64ec7923437ef |
completed | March 2, 2026, 9:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a556669878819098816d2221a3fd3d |
completed | March 2, 2026, 9:20 a.m. |
Created at: March 1, 2026, 7:35 p.m.