Triple
T1210144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kim Kyong-hui |
E25979
|
entity |
| Predicate | familyBranch |
P13166
|
FINISHED |
| Object | direct bloodline of Kim Il Sung |
—
|
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: direct bloodline of Kim Il Sung | Statement: [Kim Kyong-hui, familyBranch, direct bloodline of Kim Il Sung]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: familyBranch Context triple: [Kim Kyong-hui, familyBranch, direct bloodline of Kim Il Sung]
-
A.
familyAspect
Indicates a relationship where one entity is characterized by a particular familial role, status, or aspect in relation to another entity.
-
B.
dynasticBranch
chosen
Indicates a genealogical relationship where one lineage or house originates from, or is a subordinate offshoot of, a larger parent dynasty.
-
C.
hasFamilialTieTo
Indicates a relationship where two entities are connected by family bonds, such as by blood, marriage, or adoption.
-
D.
familySize
Indicates the number of individuals that belong to a given family unit.
-
E.
family
Indicates a familial relationship or connection between entities, such as being related by blood, marriage, or adoption.
- 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_69a4942b30f08190a91c60573e16b5ef |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bde4670481908c16a3a8c1a54aad |
completed | March 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6078088190ba0221ae3368416c |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:46 p.m.