Triple
T21362085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsukuba |
E526806
|
entity |
| Predicate | hasSisterCity |
P919
|
FINISHED |
| Object | Qingdao |
—
|
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: Qingdao | Statement: [Tsukuba, hasSisterCity, Qingdao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qingdao Context triple: [Tsukuba, hasSisterCity, Qingdao]
-
A.
Qingdao
chosen
Qingdao is a major coastal city in eastern China known for its port, beaches, German colonial architecture, and Tsingtao Brewery.
-
B.
青島
青島 is a small Japanese island best known for its large population of semi-feral cats that attract many tourists.
-
C.
Weihai
Weihai is a coastal city in eastern China known for its strategic location on the Yellow Sea, maritime history, and role as a major port and tourist destination.
-
D.
Yantai
Yantai is a coastal city in Shandong Province, China, known for its port, wine production, and scenic beaches along the Bohai Sea.
-
E.
Jiaozhou
Jiaozhou is a county-level city under Qingdao in Shandong Province, China, known as a regional transport hub and industrial center on the Jiaozhou Bay.
- 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_69e0b51d8a308190b09113b3b3f9bc15 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b06b219c81908f7674ae459e7931 |
completed | April 22, 2026, 11:26 a.m. |
Created at: April 16, 2026, 5:08 p.m.