Triple
T14380478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beijing Capital Airlines |
E356586
|
entity |
| Predicate | focusCity |
P164
|
FINISHED |
| Object | Qingdao |
E130067
|
NE FINISHED |
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: [Beijing Capital Airlines, focusCity, Qingdao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qingdao Context triple: [Beijing Capital Airlines, focusCity, 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.
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.
-
C.
Yantai
Yantai is a coastal city in Shandong Province, China, known for its port, wine production, and scenic beaches along the Bohai Sea.
-
D.
Weifang
Weifang is a prefecture-level city in eastern China known for its kite-making tradition and annual international kite festival.
-
E.
Rizhao
Rizhao is a coastal city in eastern China known for its sunny climate, beaches, and port on the Yellow Sea.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900bbfb08190a1e56f281a2374c0 |
completed | April 14, 2026, 7:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd7a36382481909a39ba5e51084051 |
completed | May 8, 2026, 5:52 a.m. |
Created at: April 10, 2026, 1:16 a.m.