Triple
T9987374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Non-Aligned Movement summits |
E196800
|
entity |
| Predicate | hasSubEventType |
P6285
|
FINISHED |
| Object | ministerial meetings |
—
|
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: ministerial meetings | Statement: [Non-Aligned Movement summits, hasSubEventType, ministerial meetings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubEventType Context triple: [Non-Aligned Movement summits, hasSubEventType, ministerial meetings]
-
A.
hasSubEvent
chosen
Indicates that an event is composed of, or includes as part of its structure, another event that occurs within it.
-
B.
hasEventType
Indicates that an event is associated with, or classified under, a specific type or category of event.
-
C.
hasSubPeriod
Indicates that a time period is composed of or contains another, more specific time period as a subordinate part.
-
D.
hasSubSeries
Indicates that one series is a subordinate or component series within a larger parent series.
-
E.
hasSubsidiaryActivity
Indicates that an entity carries out an additional, secondary activity alongside its main or primary activity.
- 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_69ca82f1678c819093d06320a05f16a4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdc79c8b80819091dc16ac8fd0c720 |
completed | April 2, 2026, 1:34 a.m. |
| PD | Predicate disambiguation | batch_69cd1da07db88190945bcdab3ca82e71 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:50 p.m.