Triple
T18306722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanxia District |
E438504
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Shenkeng District |
—
|
NE NERFINISHED |
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: Shenkeng District | Statement: [Sanxia District, borderedBy, Shenkeng District]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shenkeng District Context triple: [Sanxia District, borderedBy, Shenkeng District]
-
A.
Shenkeng District
chosen
Shenkeng District is a suburban district of New Taipei City in northern Taiwan, best known for its historic old street and specialty stinky tofu cuisine.
-
B.
Shuncheng District
Shuncheng District is an urban district and administrative center of Fushun City in Liaoning Province, northeastern China.
-
C.
Fumian District
Fumian District is an administrative district under the jurisdiction of Yulin City in Guangxi, China, known for its role in regional industry and commerce.
-
D.
Shigu District
Shigu District is an urban administrative district of Hengyang City in Hunan Province, China, known as one of its central built-up areas.
-
E.
Daxi District
Daxi District is a historic district in Taoyuan, Taiwan, known for its preserved old streets, traditional wooden architecture, and cultural heritage.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5021519a481908a9b6561946f1c65 |
completed | April 19, 2026, 4:25 p.m. |
Created at: April 10, 2026, 10:35 a.m.