Triple
T19885722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gusu District |
E477894
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Shantang Street |
—
|
NE NERFINISHED |
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: Shantang Street | Statement: [Gusu District, contains, Shantang Street]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shantang Street Context triple: [Gusu District, contains, Shantang Street]
-
A.
Shantang Street
chosen
Shantang Street is a historic canal-side street in Suzhou famed for its traditional architecture, waterways, and vibrant shops and teahouses.
-
B.
Caishikou Street
Caishikou Street is a historic thoroughfare in Beijing, China, known for its traditional markets, shops, and role as a major commercial and cultural artery in the city.
-
C.
Guozijian Street
Guozijian Street is a historic lane in Beijing known for its traditional architecture and proximity to the ancient Imperial College and Confucius Temple.
-
D.
Emei Street
Emei Street is a well-known thoroughfare in Taipei’s Ximending district, noted for its dense concentration of shops, eateries, and youth-oriented nightlife.
-
E.
Yonghegong Street
Yonghegong Street is a road in Beijing, China, located in the area surrounding the historic Yonghe (Lama) Temple.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65909fe0481908e22b60d04fe2b11 |
completed | April 20, 2026, 4:49 p.m. |
Created at: April 10, 2026, 1:52 p.m.