Triple
T1517414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rajshahi |
E32151
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object |
Clean City
Clean City is a popular nickname for Rajshahi, a major city in western Bangladesh known for its cleanliness and greenery.
|
E172976
|
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: Clean City | Statement: [Rajshahi, nickname, Clean City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clean City Context triple: [Rajshahi, nickname, Clean City]
-
A.
Chocolate City
Chocolate City is a popular nickname for Washington, D.C., highlighting its historically large and influential African American population and culture.
-
B.
Green City in the Sun
Green City in the Sun is a popular nickname for Nairobi, highlighting the Kenyan capital’s lush greenery and warm, sunny climate.
-
C.
The People’s City
The People’s City is the official motto of Jefferson City, Missouri, emphasizing its identity as a community-focused and citizen-centered capital.
-
D.
Paper City
Paper City is the nickname of Holyoke, Massachusetts, reflecting its historic prominence as a major center of paper manufacturing.
-
E.
The City of Good Living
The City of Good Living is a promotional nickname highlighting the comfortable, family-friendly quality of life in San Carlos, California.
- 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: Clean City Triple: [Rajshahi, nickname, Clean City]
Generated description
Clean City is a popular nickname for Rajshahi, a major city in western Bangladesh known for its cleanliness and greenery.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Clean City Target entity description: Clean City is a popular nickname for Rajshahi, a major city in western Bangladesh known for its cleanliness and greenery.
-
A.
Chocolate City
Chocolate City is a popular nickname for Washington, D.C., highlighting its historically large and influential African American population and culture.
-
B.
Green City in the Sun
Green City in the Sun is a popular nickname for Nairobi, highlighting the Kenyan capital’s lush greenery and warm, sunny climate.
-
C.
The People’s City
The People’s City is the official motto of Jefferson City, Missouri, emphasizing its identity as a community-focused and citizen-centered capital.
-
D.
Paper City
Paper City is the nickname of Holyoke, Massachusetts, reflecting its historic prominence as a major center of paper manufacturing.
-
E.
The City of Good Living
The City of Good Living is a promotional nickname highlighting the comfortable, family-friendly quality of life in San Carlos, California.
- 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_69a885e8caf88190a5fbb6159ce87786 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a907eb7d108190bf26199744d510d7 |
completed | March 5, 2026, 4:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad2344f8d8819082e1ae5c980d0525 |
completed | March 8, 2026, 7:20 a.m. |
| NEDg | Description generation | batch_69ad23d86d088190bbea03d5d49bc009 |
completed | March 8, 2026, 7:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad2459c38c8190a8c166c2743a8936 |
completed | March 8, 2026, 7:25 a.m. |
Created at: March 4, 2026, 7:26 p.m.