Triple
T37157366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mohammadzai |
E920544
|
entity |
| Predicate | founderOfRule |
P77474
|
FINISHED |
| Object | Dost Mohammad 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: Dost Mohammad Khan | Statement: [Mohammadzai, founderOfRule, Dost Mohammad Khan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: founderOfRule Context triple: [Mohammadzai, founderOfRule, Dost Mohammad Khan]
-
A.
royalHouseFounder
chosen
Indicates that one entity is the person who founded or established the royal house or dynasty to which the other entity belongs.
-
B.
founderOfPredecessor
Indicates that an entity is the founder of another entity that served as a predecessor to a specified organization or institution.
-
C.
dynastyFoundedRuledRegion
Indicates that a particular dynasty was established and exercised ruling authority over a specified region.
-
D.
foundingEmperor
Indicates the person who established or first ruled an empire as its original sovereign.
-
E.
fatherIsRulerOf
Indicates that the person who is the father holds the position of ruler or sovereign over the specified entity or domain.
- 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_69f76ea0429081908c711b55599eac3c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff38b960808190a8263348f1e5c0e4 |
completed | May 9, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69ff37d97d9c8190849b2bac14f9af1d |
completed | May 9, 2026, 1:34 p.m. |
Created at: May 3, 2026, 4:15 p.m.