Triple
T3637946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shilin Night Market |
E77115
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Shilin |
E313956
|
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: Shilin | Statement: [Shilin Night Market, region, Shilin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shilin Context triple: [Shilin Night Market, region, Shilin]
-
A.
Xinyi
Xinyi is a county-level city administered by Xuzhou in Jiangsu Province, eastern China.
-
B.
Jiufen
Jiufen is a historic hillside town in northern Taiwan famed for its narrow lantern-lit streets, teahouses, and scenic views over the Pacific Ocean.
-
C.
Shilin District
chosen
Shilin District is a populous and historically rich administrative district in northern Taipei, Taiwan, known for its famous night market, cultural attractions, and educational institutions.
-
D.
Nantou
Nantou is a historic subdistrict in Shenzhen’s Nanshan District, known as the site of the old county seat and a preserved ancient town area.
-
E.
Tainan
Tainan is a historic city in southern Taiwan known for its well-preserved temples, traditional culture, and status as the island’s former capital.
- 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_69ad85dd0be48190b738990cb20c4731 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc328e5e481909d26318c743bc84a |
completed | March 8, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b488320c58819088f8cc677f675ec3 |
completed | March 13, 2026, 9:57 p.m. |
Created at: March 8, 2026, 3:24 p.m.