Triple
T11674942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Presidential Office Building, Taipei |
E277466
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object |
Bo’ai Road
Bo’ai Road is a street in central Taipei, Taiwan, known for its proximity to key government buildings and historic sites.
|
E940369
|
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: Bo’ai Road | Statement: [Presidential Office Building, Taipei, near, Bo’ai Road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bo’ai Road Context triple: [Presidential Office Building, Taipei, near, Bo’ai Road]
-
A.
Anfu Road
Anfu Road is a leafy, boutique-lined street in Shanghai known for its trendy cafés, independent shops, and preserved European-style architecture.
-
B.
Longyang Road
Longyang Road is a major thoroughfare in Shanghai, China, known for serving as a key transportation corridor in the Pudong area.
-
C.
Yishan Road
Yishan Road is a Shanghai Metro interchange station serving multiple lines in the Xuhui District of Shanghai, China.
-
D.
Changle Road
Changle Road is a historic, tree-lined street in Shanghai known for its European-style architecture, boutiques, and cafés dating back to the city’s colonial era.
-
E.
Hangzhong Road
Hangzhong Road is a Shanghai Metro station that serves as a terminus on a branch of Line 10 in Shanghai, China.
- 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: Bo’ai Road Triple: [Presidential Office Building, Taipei, near, Bo’ai Road]
Generated description
Bo’ai Road is a street in central Taipei, Taiwan, known for its proximity to key government buildings and historic sites.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bo’ai Road Target entity description: Bo’ai Road is a street in central Taipei, Taiwan, known for its proximity to key government buildings and historic sites.
-
A.
Anfu Road
Anfu Road is a leafy, boutique-lined street in Shanghai known for its trendy cafés, independent shops, and preserved European-style architecture.
-
B.
Longyang Road
Longyang Road is a major thoroughfare in Shanghai, China, known for serving as a key transportation corridor in the Pudong area.
-
C.
Yishan Road
Yishan Road is a Shanghai Metro interchange station serving multiple lines in the Xuhui District of Shanghai, China.
-
D.
Changle Road
Changle Road is a historic, tree-lined street in Shanghai known for its European-style architecture, boutiques, and cafés dating back to the city’s colonial era.
-
E.
Hangzhong Road
Hangzhong Road is a Shanghai Metro station that serves as a terminus on a branch of Line 10 in Shanghai, China.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a44504c48190b519765a83ff9c5e |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef13f12c2481909171a3237064c76d |
completed | April 27, 2026, 7:44 a.m. |
| NEDg | Description generation | batch_69ef3551b9a88190a9b30bcb2592628b |
completed | April 27, 2026, 10:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ef51c17078819083f05036f290ce09 |
completed | April 27, 2026, 12:08 p.m. |
Created at: April 8, 2026, 9:40 p.m.