Triple
T10690992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suzhou Creek |
E252006
|
entity |
| Predicate | hasBridge |
P386
|
FINISHED |
| Object | Waibaidu Bridge |
E212070
|
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: Waibaidu Bridge | Statement: [Suzhou Creek, hasBridge, Waibaidu Bridge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waibaidu Bridge Context triple: [Suzhou Creek, hasBridge, Waibaidu Bridge]
-
A.
Waibaidu Bridge
chosen
Waibaidu Bridge is a historic steel truss bridge in Shanghai, China, renowned as one of the city’s most iconic river crossings and architectural landmarks.
-
B.
Chengmei Bridge
Chengmei Bridge is a notable road bridge spanning the Keelung River in Taipei, Taiwan, serving as an important local transportation link.
-
C.
Qiansimen Bridge
Qiansimen Bridge is a prominent cable-stayed road and rail bridge spanning the Jialing River in Chongqing, China, known for its striking red structure and views of the city’s skyline.
-
D.
Guandu Bridge
Guandu Bridge is a prominent red arch bridge in New Taipei City, Taiwan, known for carrying road traffic across the Tamsui River and serving as a local landmark.
-
E.
Guomao Bridge
Guomao Bridge is a major multi-level traffic interchange in Beijing’s central business district, serving as a key junction for both road transport and nearby metro lines.
- 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_69d6aa5bd7c08190a816e733b4045c23 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fd3705788190bcbdef93b4c5f574 |
completed | April 9, 2026, 1:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d988a59d6c8190a0e170acfb3af6da |
completed | April 10, 2026, 11:32 p.m. |
Created at: April 8, 2026, 9:11 p.m.