Triple
T1135704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bonn |
E23133
|
entity |
| Predicate | twinCity |
P1072
|
FINISHED |
| Object | Ulaanbaatar |
E24958
|
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: Ulaanbaatar | Statement: [Bonn, twinCity, Ulaanbaatar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ulaanbaatar Context triple: [Bonn, twinCity, Ulaanbaatar]
-
A.
Ulaanbaatar
chosen
Ulaanbaatar is the capital and largest city of Mongolia, serving as its political, economic, and cultural center.
-
B.
Hohhot
Hohhot is the capital and largest city of Inner Mongolia in northern China, known as a regional center of politics, culture, and industry.
-
C.
Öndörkhaan, Mongolia
Öndörkhaan is a town in eastern Mongolia known historically as the site where Chinese marshal Lin Biao died in a 1971 plane crash.
-
D.
Blagoveshchensk
Blagoveshchensk is a Russian city in the Amur Oblast that serves as an important administrative and economic center on the border with China, directly across the Amur River from Heihe.
-
E.
Almaty
Almaty is the largest city and main commercial and cultural center of Kazakhstan, located in the country’s mountainous southeast.
- 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_69a493ec75988190b63a11bafaec29b4 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bc2300c481908c60fbb1188c37c5 |
completed | March 1, 2026, 10:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac59ae5f20819093f8acc3ba7a6638 |
completed | March 7, 2026, 5 p.m. |
Created at: March 1, 2026, 7:44 p.m.