Triple
T15645842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taipei Songshan Airport |
E376173
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | Taipei Songshan |
E77117
|
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: Taipei Songshan | Statement: [Taipei Songshan Airport, alternativeName, Taipei Songshan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taipei Songshan Context triple: [Taipei Songshan Airport, alternativeName, Taipei Songshan]
-
A.
Taipei Songshan Airport
chosen
Taipei Songshan Airport is a domestic and regional international airport located near the center of Taipei, Taiwan, serving as a key hub for short-haul flights.
-
B.
Xinyi
Xinyi is a county-level city administered by Maoming in Guangdong Province, China, known for its agriculture and regional commerce.
-
C.
Xinyi
Xinyi is a county-level city administered by Xuzhou in Jiangsu Province, eastern China.
-
D.
Chungshan
Chungshan is an older romanization of Zhongshan, a major city in Guangdong Province, China, named in honor of Sun Yat-sen.
-
E.
Hsiu-chu
Hsiu-chu is a feminine given name of Chinese origin, notably borne by Taiwanese politician Hung Hsiu-chu.
- 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_69d85cd1564c8190991adda63bfab4b0 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04ed5b8b081908d7127964eed3b09 |
completed | April 16, 2026, 2:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff875e49748190a2a4aceb649762b4 |
completed | May 9, 2026, 7:13 p.m. |
Created at: April 10, 2026, 4:15 a.m.