Triple
T5033664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blagoveshchensk |
E113367
|
entity |
| Predicate | hasSisterCity |
P919
|
FINISHED |
| Object | Heihe |
E171068
|
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: Heihe | Statement: [Blagoveshchensk, hasSisterCity, Heihe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Heihe Context triple: [Blagoveshchensk, hasSisterCity, Heihe]
-
A.
Heihe
chosen
Heihe is a northeastern Chinese border city in Heilongjiang province, located opposite the Russian city of Blagoveshchensk and known as a key hub for Sino-Russian trade and cross-border relations.
-
B.
Luohe
Luohe is a prefecture-level city in central Henan Province, China, known as an important regional transport and industrial hub.
-
C.
Tongliao
Tongliao is a prefecture-level city in eastern Inner Mongolia, China, known as a regional hub for agriculture, animal husbandry, and Mongolian culture.
-
D.
Qiqihar
Qiqihar is a major industrial city in northeastern China’s Heilongjiang province, known historically as a regional transportation hub and center for heavy industry.
-
E.
Wuhai
Wuhai is a prefecture-level industrial city in western Inner Mongolia, China, known for its coal mining, chemical industries, and location along the Yellow River.
- 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_69bd443775e48190a646ffbfc4334723 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73b68d8c8190b8e04fb406abdb0f |
completed | March 20, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69befe4abf2c81908946d4ab18b7273d |
completed | March 21, 2026, 8:23 p.m. |
Created at: March 20, 2026, 1:36 p.m.