Triple
T32248766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Admission of Indonesia |
E823824
|
entity |
| Predicate | recommendingOrgan |
P5662
|
FINISHED |
| Object | United Nations Security Council |
—
|
NE NERFINISHED |
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 Security Council | Statement: [Admission of Indonesia, recommendingOrgan, United Nations Security Council]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recommendingOrgan Context triple: [Admission of Indonesia, recommendingOrgan, United Nations Security Council]
-
A.
recommendationProcess
Indicates the process by which one entity evaluates options and suggests a preferred choice or course of action to another entity.
-
B.
recommendation
chosen
Indicates that one entity suggests, endorses, or advises another entity as suitable or beneficial for a particular purpose or context.
-
C.
organOrganization
Indicates that an organ is structurally or functionally part of, or associated with, a specific organization or organizational system.
-
D.
recommendedLocation
Indicates that one entity suggests or endorses another entity as a suitable or preferred place for a particular purpose or activity.
-
E.
recommendedIn
Indicates that one entity is suggested or endorsed within the context, content, or scope of another entity (such as a document, list, or recommendation source).
- 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_69f3490cdda88190a9d61e11252a771f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6d16f5cb881908eed141afaaa0b51 |
completed | May 3, 2026, 4:39 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe45554819089cbbd538d992132 |
completed | May 3, 2026, 4:32 a.m. |
Created at: May 1, 2026, 12:40 a.m.