Triple
T15688170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rehe |
E380255
|
entity |
| Predicate | chineseName |
P4878
|
FINISHED |
| Object | 熱河 |
E145651
|
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: 熱河 | Statement: [Rehe, chineseName, 熱河]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 熱河 Context triple: [Rehe, chineseName, 熱河]
-
A.
Luohe
Luohe is a prefecture-level city in central Henan Province, China, known as an important regional transport and industrial hub.
-
B.
Chengde
chosen
Chengde is a historic city in northeastern China best known for its Qing dynasty Mountain Resort, a vast imperial summer retreat and UNESCO World Heritage Site.
-
C.
Heihe
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.
-
D.
Xuanhuai
Xuanhuai is the given name of Sheng Xuanhuai, a prominent late Qing dynasty Chinese official, industrialist, and key figure in the Self-Strengthening Movement.
-
E.
Guanghe
Guanghe was an era name used during the reign of Emperor Ling of the Eastern Han dynasty in ancient China.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f4cee5481908699fbb2b7bdd2f6 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ee91340819086c8f51e8eb477aa |
completed | May 9, 2026, 5:29 p.m. |
Created at: April 10, 2026, 4:44 a.m.