Triple
T19529999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heaven Lake |
E488630
|
entity |
| Predicate | governingCountrySide |
P17189
|
FINISHED |
| Object | Chinese side administered by Jilin Province |
—
|
LITERAL 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: Chinese side administered by Jilin Province | Statement: [Heaven Lake, governingCountrySide, Chinese side administered by Jilin Province]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governingCountrySide Context triple: [Heaven Lake, governingCountrySide, Chinese side administered by Jilin Province]
-
A.
nationalSideOf
Indicates that one entity is the national team or national representative side associated with another entity, such as a country or nation.
-
B.
regionCountrySide
Indicates that a region is located in or associated with the countryside or rural area of a country.
-
C.
countryOnOneSide
chosen
Indicates that one entity is located on one side or border of a specified country.
-
D.
governingBodyCountry
Indicates the country within whose jurisdiction or authority a governing body operates or to which it officially belongs.
-
E.
governingSystemCountry
Indicates that a particular system of governance is the ruling or official governing system used by a given country.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363dfd6c8190aaa0b374184965bb |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.