Triple
T14753690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yongding River |
E346676
|
entity |
| Predicate | crosses |
P416
|
FINISHED |
| Object | Lugou Bridge |
E317829
|
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: Lugou Bridge | Statement: [Yongding River, crosses, Lugou Bridge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lugou Bridge Context triple: [Yongding River, crosses, Lugou Bridge]
-
A.
Lugou Bridge
chosen
Lugou Bridge, also known as the Marco Polo Bridge, is a historic stone arch bridge in Beijing famous as the site where the Second Sino-Japanese War began in 1937.
-
B.
Andingmen Bridge
Andingmen Bridge is a major traffic overpass and landmark in Beijing, China, located near the historic Andingmen area of the city.
-
C.
Yongle Bridge
Yongle Bridge is a notable bridge in Tianjin, China, best known for supporting the iconic Tianjin Eye Ferris wheel that spans the Hai River.
-
D.
Waibaidu Bridge
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.
-
E.
Yongdingmen Bridge
Yongdingmen Bridge is a road bridge in Beijing, China, named after and located near the historic Yongdingmen city gate area.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec7d59df08190a86da5048358bd6e |
completed | April 14, 2026, 11:03 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe0cea5d348190a84970da131292ee |
completed | May 8, 2026, 4:18 p.m. |
Created at: April 10, 2026, 1:30 a.m.