Triple
T31520131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emir Abdur Rahman Khan |
E804184
|
entity |
| Predicate | convertedRegionRenamedAs |
P52429
|
FINISHED |
| Object | Nuristan |
—
|
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: Nuristan | Statement: [Emir Abdur Rahman Khan, convertedRegionRenamedAs, Nuristan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: convertedRegionRenamedAs Context triple: [Emir Abdur Rahman Khan, convertedRegionRenamedAs, Nuristan]
-
A.
convertedRegion
Indicates that one region has been transformed, adapted, or changed into another region or regional form.
-
B.
renamedTerritory
chosen
Indicates that an existing territory has been given a new official name, linking the former designation to its updated one.
-
C.
reorganisedRegion
Indicates that a region has undergone a structural or administrative change, resulting in a new or altered regional configuration.
-
D.
realmRenamedFrom
Indicates that a realm currently known by one name previously had a different name from which it was renamed.
-
E.
relocatedAndRenamed
Indicates that an entity has moved from one location to another and changed its name as part of that move.
- 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_69f348cf839c81908657048402f7f97b |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 30, 2026, 9:55 p.m.