Triple
T17758961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gwangju, Gyeonggi |
E443317
|
entity |
| Predicate | hasHistoricalSite |
P1098
|
FINISHED |
| Object | Namhan Fortress vicinity |
—
|
NE NERFINISHED |
How this triple was built (3 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: Namhan Fortress vicinity | Statement: [Gwangju, Gyeonggi, hasHistoricalSite, Namhan Fortress vicinity]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Namhan Fortress vicinity Context triple: [Gwangju, Gyeonggi, hasHistoricalSite, Namhan Fortress vicinity]
-
A.
Ulaan Khar fortress
Ulaan Khar fortress is an ancient defensive stronghold in Mongolia, notable for its historical role in regional military and trade networks.
-
B.
Ananuri Fortress
Ananuri Fortress is a historic medieval castle complex in Georgia, renowned for its strategic location overlooking the Aragvi River and its well-preserved defensive towers and churches.
-
C.
Tsitsamuri fortress
Tsitsamuri fortress is a historic hilltop stronghold in Georgia that once served as a strategic defensive site overlooking the surrounding region.
-
D.
K’alla Q’asa fortress area
K’alla Q’asa fortress area is a defensive hilltop sector of the Pisac archaeological complex in Peru, known for its strategic location and Inca military architecture.
-
E.
Narikala Fortress
Narikala Fortress is an ancient hilltop fortification overlooking Tbilisi, Georgia, known as one of the city’s most iconic historical landmarks.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Namhan Fortress vicinity Target entity description: Namhan Fortress vicinity is a historically significant area surrounding the mountain fortress of Namhansanseong in Gwangju, Gyeonggi Province, known for its Joseon-era military heritage and scenic natural landscape.
-
A.
Ulaan Khar fortress
Ulaan Khar fortress is an ancient defensive stronghold in Mongolia, notable for its historical role in regional military and trade networks.
-
B.
Ananuri Fortress
Ananuri Fortress is a historic medieval castle complex in Georgia, renowned for its strategic location overlooking the Aragvi River and its well-preserved defensive towers and churches.
-
C.
Tsitsamuri fortress
Tsitsamuri fortress is a historic hilltop stronghold in Georgia that once served as a strategic defensive site overlooking the surrounding region.
-
D.
K’alla Q’asa fortress area
K’alla Q’asa fortress area is a defensive hilltop sector of the Pisac archaeological complex in Peru, known for its strategic location and Inca military architecture.
-
E.
Narikala Fortress
Narikala Fortress is an ancient hilltop fortification overlooking Tbilisi, Georgia, known as one of the city’s most iconic historical landmarks.
- F. None of above. chosen
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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48420ad188190aeb0f4ec1d23ee5c |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 10:10 a.m.