Triple
T36501272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kushk District |
E899333
|
entity |
| Predicate | borderSecurityResponsibilityOf |
P198142
|
FINISHED |
| Object | Afghan authorities |
—
|
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: Afghan authorities | Statement: [Kushk District, borderSecurityResponsibilityOf, Afghan authorities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderSecurityResponsibilityOf Context triple: [Kushk District, borderSecurityResponsibilityOf, Afghan authorities]
-
A.
borderConcern
Indicates a relationship where one entity has issues, disputes, or security considerations related to its shared boundary or border with another entity.
-
B.
borderRegime
Indicates the type, rules, or control system governing how movement or interaction is managed across a border between entities.
-
C.
borderGuardDuty
chosen
Indicates that an entity is assigned to perform security or monitoring duties at a border or checkpoint.
-
D.
responsibleForBorder
Indicates that an entity has authority or duty to manage, control, or oversee a specific border or boundary.
-
E.
borderDepartment
Indicates that one administrative department directly borders or shares a boundary with another department.
- 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_69f76e5b92088190933afda3f7531dd4 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffdf47d9608190830ca23d9cef6409 |
completed | May 10, 2026, 1:28 a.m. |
| PD | Predicate disambiguation | batch_69ffdf00e2b4819082dd5cb78f316baf |
completed | May 10, 2026, 1:27 a.m. |
Created at: May 3, 2026, 4:10 p.m.