Triple
T17956533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhaoqing |
E448964
|
entity |
| Predicate | hasTouristAttraction |
P530
|
FINISHED |
| Object | Ancient City Wall of Zhaoqing |
—
|
NE NERFINISHED |
How this triple was built (3 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: Ancient City Wall of Zhaoqing | Statement: [Zhaoqing, hasTouristAttraction, Ancient City Wall of Zhaoqing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ancient City Wall of Zhaoqing Context triple: [Zhaoqing, hasTouristAttraction, Ancient City Wall of Zhaoqing]
-
A.
Ancient City Wall of Guangzhou
The Ancient City Wall of Guangzhou is a historic fortification remnant in Guangzhou, China, reflecting the city’s traditional defensive architecture and long urban history.
-
B.
Pingyao City Wall
Pingyao City Wall is a well-preserved Ming-era defensive fortification encircling the ancient city of Pingyao in Shanxi, China, renowned for its intact ramparts, gates, and watchtowers.
-
C.
Fengshan Old City walls
Fengshan Old City walls are the historic defensive fortifications of the former Fengshan County in today’s Kaohsiung, Taiwan, preserved as a cultural and architectural heritage site.
-
D.
Jingzhou Ancient City Wall
Jingzhou Ancient City Wall is a well-preserved, large-scale defensive fortification from imperial China, renowned for encircling the historic city of Jingzhou in Hubei Province and showcasing traditional brick-and-earth city wall architecture.
-
E.
Nanjing City Wall
The Nanjing City Wall is a massive Ming dynasty fortification encircling much of Nanjing, renowned as one of the longest and best-preserved ancient city walls in the world.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ancient City Wall of Zhaoqing Target entity description: The Ancient City Wall of Zhaoqing is a historic fortification in Guangdong, China, renowned for its well-preserved Ming-era architecture and scenic views over the surrounding city and lakes.
-
A.
Ancient City Wall of Guangzhou
The Ancient City Wall of Guangzhou is a historic fortification remnant in Guangzhou, China, reflecting the city’s traditional defensive architecture and long urban history.
-
B.
Pingyao City Wall
Pingyao City Wall is a well-preserved Ming-era defensive fortification encircling the ancient city of Pingyao in Shanxi, China, renowned for its intact ramparts, gates, and watchtowers.
-
C.
Fengshan Old City walls
Fengshan Old City walls are the historic defensive fortifications of the former Fengshan County in today’s Kaohsiung, Taiwan, preserved as a cultural and architectural heritage site.
-
D.
Jingzhou Ancient City Wall
Jingzhou Ancient City Wall is a well-preserved, large-scale defensive fortification from imperial China, renowned for encircling the historic city of Jingzhou in Hubei Province and showcasing traditional brick-and-earth city wall architecture.
-
E.
Nanjing City Wall
The Nanjing City Wall is a massive Ming dynasty fortification encircling much of Nanjing, renowned as one of the longest and best-preserved ancient city walls in the world.
- F. None of above. chosen
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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afb0afe08190964e771ec632fa1e |
completed | April 19, 2026, 10:34 a.m. |
Created at: April 10, 2026, 10:21 a.m.