Triple
T3929740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Min River (Fujian) |
E93366
|
entity |
| Predicate | sourceLocatedIn |
P409
|
FINISHED |
| Object | northwestern Fujian |
E41238
|
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: northwestern Fujian | Statement: [Min River (Fujian), sourceLocatedIn, northwestern Fujian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: northwestern Fujian Context triple: [Min River (Fujian), sourceLocatedIn, northwestern Fujian]
-
A.
Fujian
chosen
Fujian is a coastal province in southeastern China known for its significant role in Chinese migration, distinctive Min culture and dialects, and historic maritime trade.
-
B.
northwestern Hunan
Northwestern Hunan is a subregion of China’s Hunan Province characterized by its inland location, river plains, and a mix of urban centers and agricultural areas.
-
C.
Jilong
Jilong is a major port city in northern Taiwan, known in English as Keelung.
-
D.
Chaoshan region
The Chaoshan region is an area in eastern Guangdong, China, known for its distinct Teochew culture, language, and cuisine.
-
E.
Ningde
Ningde is a coastal prefecture-level city in northeastern Fujian Province, China, known for its mountainous landscapes, marine economy, and as the headquarters of battery giant CATL.
- 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_69aed96bfa1081908f7b30f2c647dee6 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeeda7cf3c81909df30744bddbad7e |
completed | March 9, 2026, 3:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5288094408190b5fece72ead94ec1 |
completed | March 14, 2026, 9:21 a.m. |
Created at: March 9, 2026, 3:23 p.m.