Triple
T6095315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Supreme People’s Assembly of North Korea |
E135861
|
entity |
| Predicate | meetsInSessions |
P3123
|
FINISHED |
| Object | infrequently |
—
|
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: infrequently | Statement: [Supreme People’s Assembly of North Korea, meetsInSessions, infrequently]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meetsInSessions Context triple: [Supreme People’s Assembly of North Korea, meetsInSessions, infrequently]
-
A.
meetsBetweenSessionsOf
Indicates that one entity meets another during the interval between scheduled sessions or events.
-
B.
meetsDuring
chosen
Indicates that one entity encounters or comes together with another while a specified event or time interval is in progress.
-
C.
metInFirstSession
Indicates that the entities first met or were introduced to each other during the initial session of an event, program, or interaction.
-
D.
meetsBy
Indicates that one entity encounters or comes together with another entity, typically at a specific time or place.
-
E.
sessionOf
Indicates that one entity is a session that belongs to, occurs within, or is associated with another entity (such as an event, course, or meeting series).
- 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_69c0087cd3c48190b459848c72d84eb1 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05a963bac8190bc0c33fef187875c |
completed | March 22, 2026, 9:09 p.m. |
| PD | Predicate disambiguation | batch_69c049f5ac988190b62ba565153aaa35 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:12 p.m.