Triple
T1824217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korean constitution |
E40612
|
entity |
| Predicate | formOfState |
P21555
|
FINISHED |
| Object | socialist state |
—
|
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: socialist state | Statement: [North Korean constitution, formOfState, socialist state]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formOfState Context triple: [North Korean constitution, formOfState, socialist state]
-
A.
governmentFormOfRuledState
chosen
Indicates the type of governmental system or structure by which a particular state or territory is ruled.
-
B.
stateRock
Indicates that an entity is in a solid, rock-like physical state or condition.
-
C.
formerState
Indicates that an entity previously held the status or condition of a particular state but no longer does so.
-
D.
statehoodFrom
Indicates the point in time from which an entity has held official statehood or recognized status as a state.
-
E.
statehoodContext
Indicates the contextual circumstances, conditions, or framework under which an entity’s status as a state (or its statehood) is defined, recognized, or discussed.
- 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_69a8864644bc8190b2358ab897194ac1 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab21ab83a48190a33afe5db19a21f8 |
completed | March 6, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69aa61d97d008190b6642aef32eb7e36 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:32 p.m.