Triple
T27356278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karenni National Progressive Party |
E685693
|
entity |
| Predicate | armedWingInstanceOf |
P25765
|
FINISHED |
| Object | ethnic armed organization |
—
|
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: ethnic armed organization | Statement: [Karenni National Progressive Party, armedWingInstanceOf, ethnic armed organization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armedWingInstanceOf Context triple: [Karenni National Progressive Party, armedWingInstanceOf, ethnic armed organization]
-
A.
hasArmedWing
chosen
Indicates that an entity maintains, controls, or is associated with an organized armed or military wing.
-
B.
hasWingIn
Indicates that an entity possesses a wing that is located in or contained within another specified entity or structure.
-
C.
hasWingOf
Indicates that one entity possesses or is associated with the wing that belongs to another entity.
-
D.
armedWingAbbreviation
Indicates that the object is an abbreviation or short-form name used specifically for the subject’s armed wing.
-
E.
airWingType
Indicates the classification or category of an air wing associated with an 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62c1dec70819087f3f891cb18d6f6 |
completed | May 2, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:51 a.m.