Triple
T21721062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seoul Subway Line 1 |
E536155
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Asan |
—
|
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: Asan | Statement: [Seoul Subway Line 1, connects, Asan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asan Context triple: [Seoul Subway Line 1, connects, Asan]
-
A.
Asan
chosen
Asan is a city in South Korea known for its hot springs, historical sites, and growing role as an industrial and educational center.
-
B.
Asanina
Asanina is a Byzantine noble family name associated with the influential Asen (Asan) dynasty.
-
C.
Asan-Maina
Asan-Maina is a village municipality on the western coast of Guam, known for its historical significance in World War II and proximity to the island’s capital, Hagåtña.
-
D.
Asen
Asen was a medieval Bulgarian noble and co-leader, with his brother Peter, of the uprising that restored the Second Bulgarian Empire in the late 12th century.
-
E.
Ansip
Ansip is the surname of Andrus Ansip, an Estonian politician and former Prime Minister of Estonia.
- 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_69e0c46c6dd88190a595375fa6ebd701 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69efd96f1fbc8190a202f834aec1a319 |
completed | April 27, 2026, 9:47 p.m. |
Created at: April 16, 2026, 6:47 p.m.