Triple
T21343849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Woody Island |
E526274
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Yongxing Town
Yongxing Town is the administrative town-level division established by China on Woody Island in the South China Sea, serving as the seat of Sansha City.
|
E1479311
|
NE FINISHED |
How this triple was built (4 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: Yongxing Town | Statement: [Woody Island, hasSettlement, Yongxing Town]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yongxing Town Context triple: [Woody Island, hasSettlement, Yongxing Town]
-
A.
Yongxing
Yongxing was a historical Chinese era name used during the reign of Emperor Daowu of the Northern Wei dynasty.
-
B.
Yongxing Township
Yongxing Township is a rural administrative township located within Nantou County in central Taiwan.
-
C.
Yingshang Town
Yingshang Town is the main urban and political hub of Yingshang County in Anhui Province, China.
-
D.
Xikou Town
Xikou Town is a historic town in Fenghua District, Ningbo, Zhejiang Province, best known as the hometown of Chiang Kai-shek and a popular cultural and tourist destination.
-
E.
Luojing Town
Luojing Town is a suburban township-level division of Shanghai, China, situated within the municipality’s northern Baoshan District.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Yongxing Town Triple: [Woody Island, hasSettlement, Yongxing Town]
Generated description
Yongxing Town is the administrative town-level division established by China on Woody Island in the South China Sea, serving as the seat of Sansha City.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Yongxing Town Target entity description: Yongxing Town is the administrative town-level division established by China on Woody Island in the South China Sea, serving as the seat of Sansha City.
-
A.
Yongxing
Yongxing was a historical Chinese era name used during the reign of Emperor Daowu of the Northern Wei dynasty.
-
B.
Yongxing Township
Yongxing Township is a rural administrative township located within Nantou County in central Taiwan.
-
C.
Yingshang Town
Yingshang Town is the main urban and political hub of Yingshang County in Anhui Province, China.
-
D.
Xikou Town
Xikou Town is a historic town in Fenghua District, Ningbo, Zhejiang Province, best known as the hometown of Chiang Kai-shek and a popular cultural and tourist destination.
-
E.
Luojing Town
Luojing Town is a suburban township-level division of Shanghai, China, situated within the municipality’s northern Baoshan District.
- F. None of above. chosen
Provenance (5 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_69e0b51c33048190ab27cede74ef798c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8a85274f481909e699b390bed9350 |
completed | April 22, 2026, 10:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09a5c8c9808190810982de97320df3 |
completed | May 17, 2026, 11:26 a.m. |
| NEDg | Description generation | batch_6a09a6848c1c8190992ae7cdfeabdcf8 |
completed | May 17, 2026, 11:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09aae23f2c81908f08d290277e22f9 |
completed | May 17, 2026, 11:47 a.m. |
Created at: April 16, 2026, 4:44 p.m.