Triple
T31520058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kafiristan |
E804183
|
entity |
| Predicate | convertedUnderRuler |
P179833
|
FINISHED |
| Object | Abdur Rahman Khan |
—
|
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: Abdur Rahman Khan | Statement: [Kafiristan, convertedUnderRuler, Abdur Rahman Khan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: convertedUnderRuler Context triple: [Kafiristan, convertedUnderRuler, Abdur Rahman Khan]
-
A.
peakUnderRuler
Indicates that a peak (such as a mountain or summit) is located within the domain or territory governed by a particular ruler.
-
B.
recognizedAsRuler
Indicates that one entity is acknowledged or accepted by others as the legitimate ruler or sovereign authority.
-
C.
involvesRuler
Indicates that the relationship or action includes or pertains to a ruler as a participating party.
-
D.
usedByRuler
Indicates that something is employed, utilized, or otherwise put to use by a ruler or governing authority.
-
E.
providedRulerFor
Indicates that one entity supplied or designated another entity to serve as the ruler or governing authority over a particular domain or group.
- F. None of above. chosen
Provenance (4 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_69f727afd5d88190ad48735cd1b32787 |
completed | May 3, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_69f72737c42c8190a3f781a5e98868ff |
completed | May 3, 2026, 10:45 a.m. |
| PDg | Predicate description generation | batch_69f727ad9ff88190ba8069dd48b2e98f |
completed | May 3, 2026, 10:47 a.m. |
Created at: April 30, 2026, 9:55 p.m.