Triple
T28500836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | De'ang |
E721224
|
entity |
| Predicate | primaryProvinceInChina |
P79461
|
FINISHED |
| Object | Yunnan Province |
—
|
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: Yunnan Province | Statement: [De'ang, primaryProvinceInChina, Yunnan Province]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryProvinceInChina Context triple: [De'ang, primaryProvinceInChina, Yunnan Province]
-
A.
otherProvinceInChina
Indicates that two provinces are distinct from each other while both being located within China.
-
B.
autonomousPrefectureInChina
Indicates that one administrative region is an autonomous prefecture located within the territorial jurisdiction of China.
-
C.
includesProvinceOnChinaSide
Indicates that a specified entity encompasses or contains a province located on the Chinese side of a border or boundary.
-
D.
mainProvinces
Indicates that certain provinces are the primary or most significant administrative regions associated with a given entity.
-
E.
baseProvince
chosen
Indicates that one administrative or territorial unit serves as the primary or originating province associated with another entity.
- F. None of above.
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_69f01a5afdac8190ac6e72d5c100bd58 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a0042524d8c8190884a10fce669ae95 |
completed | May 10, 2026, 8:31 a.m. |
| PD | Predicate disambiguation | batch_6a0041e89bd881909e32764699bcb89b |
completed | May 10, 2026, 8:29 a.m. |
Created at: April 28, 2026, 3:06 a.m.