Triple
T17349315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constance |
E421763
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Suzhou, China |
—
|
NE ONNED1 |
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: Suzhou, China | Statement: [Constance, hasTwinTown, Suzhou, China]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suzhou, China Context triple: [Constance, hasTwinTown, Suzhou, China]
-
A.
Suzhou
chosen
Suzhou is a historic and economically significant city in eastern China, renowned for its classical gardens, canals, and silk industry.
-
B.
Hsiangcheng, China
Hsiangcheng, China is a town in Henan Province known as the birthplace of author and social critic Os Guinness.
-
C.
Suzhou, Jiangsu, Republic of China
Suzhou, Jiangsu, Republic of China, is a historic city in eastern China renowned for its classical gardens, canals, and rich cultural heritage.
-
D.
Suzhou New District
Suzhou New District is a major high-tech industrial and development zone in Suzhou, China, known for its advanced manufacturing, technology enterprises, and modern infrastructure.
-
E.
Wuxi
Wuxi is a major industrial and cultural city in eastern China, located near Lake Tai and known for its manufacturing, canals, and historic gardens.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a2af5f88190b4c292ca30993b36 |
completed | April 19, 2026, 2:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01955658b88190bce3fb2b5738afc6 |
in_progress | May 11, 2026, 8:37 a.m. |
Created at: April 10, 2026, 5:44 a.m.