Triple
T19875120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fifteenth session of the United Nations General Assembly |
E477616
|
entity |
| Predicate | meetingOf |
P49217
|
FINISHED |
| Object | United Nations member states |
—
|
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: United Nations member states | Statement: [Fifteenth session of the United Nations General Assembly, meetingOf, United Nations member states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meetingOf Context triple: [Fifteenth session of the United Nations General Assembly, meetingOf, United Nations member states]
-
A.
meetingType
Indicates the specific category or format of a meeting that characterizes how it is organized or conducted.
-
B.
meeting
chosen
Indicates that two or more entities come together at the same time and place for discussion, decision-making, or coordinated activity.
-
C.
meetingsAre
Indicates that certain entities function as or are classified as meetings in relation to one another.
-
D.
plansMeetingWith
Indicates that one entity arranges or intends to organize a meeting involving another entity.
-
E.
meetingContext
Indicates the situational setting, circumstances, or background conditions in which a meeting takes place.
- 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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658d9ee108190a53cc6c8e115d0fa |
completed | April 20, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69e537e8c4e481909fe95d795b4864e7 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:52 p.m.