Triple
T119589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Member States of the United Nations |
E2413
|
entity |
| Predicate | areDividedInto |
P747
|
FINISHED |
| Object | regional groups of the United Nations |
—
|
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: regional groups of the United Nations | Statement: [Member States of the United Nations, areDividedInto, regional groups of the United Nations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: areDividedInto Context triple: [Member States of the United Nations, areDividedInto, regional groups of the United Nations]
-
A.
divisionTitle
Indicates the formal name or title assigned to a specific division within a larger organization or structure.
-
B.
hasCivilDivision
Indicates that one administrative or political entity is subdivided into, or is associated with, a specific civil division (such as a county, district, or municipality).
-
C.
separates
Indicates that one entity divides, parts, or keeps other entities apart from each other.
-
D.
hasSubdivision
chosen
Indicates that one entity is divided into and contains another entity as one of its constituent parts or administrative units.
-
E.
divisionTitles
Indicates that an entity holds or is associated with one or more titles or championships within a specific division or category.
- 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_69a2506c5428819085c28a8884790e29 |
completed | Feb. 28, 2026, 2:18 a.m. |
| NER | Named-entity recognition | batch_69a258e0b11c8190b7b5cf3c354c47ce |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25646d5088190a057989c32da3a90 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:24 a.m.