Triple
T6086691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wuhan Metro Line 4 |
E135655
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Qingshan District |
E136088
|
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: Qingshan District | Statement: [Wuhan Metro Line 4, connects, Qingshan District]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qingshan District Context triple: [Wuhan Metro Line 4, connects, Qingshan District]
-
A.
Qingshan District
chosen
Qingshan District is an urban district of Wuhan in Hubei Province, China, known for its heavy industry and riverside location along the Yangtze River.
-
B.
Xiaonan District
Xiaonan District is the central urban district and administrative seat of Xiaogan City in Hubei Province, China.
-
C.
Jinyuan District
Jinyuan District is an urban administrative district of Taiyuan, the capital city of Shanxi Province in northern China.
-
D.
Wanhua District
Wanhua District is one of Taipei’s oldest urban areas, known for its historic temples, traditional markets, and the popular shopping and entertainment area of Ximending.
-
E.
Yuhua District
Yuhua District is an urban administrative district of Changsha, the capital city of Hunan Province in south-central China.
- 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_69c0087bcc788190b20f093d3a6c60ec |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0578a8b8081908490e447ae3419f9 |
completed | March 22, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c769d6f40c8190a59df50d44c50cea |
completed | March 28, 2026, 5:40 a.m. |
Created at: March 22, 2026, 4:12 p.m.