Triple
T3637955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taipei Metro |
E77116
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Taoyuan |
E159989
|
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: Taoyuan | Statement: [Taipei Metro, serves, Taoyuan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taoyuan Context triple: [Taipei Metro, serves, Taoyuan]
-
A.
Taoyuan City
chosen
Taoyuan City is a major municipality in northwestern Taiwan known for its rapidly growing urban areas, industrial zones, and proximity to Taiwan Taoyuan International Airport.
-
B.
Xinyi
Xinyi is a county-level city administered by Xuzhou in Jiangsu Province, eastern China.
-
C.
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.
-
D.
Kaohsiung
Kaohsiung is a major port city in southern Taiwan known for its heavy industry, modern harborfront, and growing cultural and arts scene.
-
E.
Keelung
Keelung is a major port city in northeastern Taiwan known for its busy harbor, seafood markets, and coastal scenery.
- 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_69b56b316140819089c90f3e2bd81ad8 |
completed | March 14, 2026, 2:05 p.m. |
Created at: March 8, 2026, 3:24 p.m.