Triple
T7837978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ismail Khan |
E181732
|
entity |
| Predicate | controlledMilitia |
P16398
|
FINISHED |
| Object | Herat-based militia forces |
—
|
LITERAL FINISHED |
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: Herat-based militia forces | Statement: [Ismail Khan, controlledMilitia, Herat-based militia forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlledMilitia Context triple: [Ismail Khan, controlledMilitia, Herat-based militia forces]
-
A.
militaryControl
chosen
Indicates that one entity exercises authoritative military power, command, or occupation over another entity or territory.
-
B.
paramilitaryWing
Indicates that one entity functions as the paramilitary or armed wing associated with another entity, typically an organization or movement.
-
C.
paramilitary
Indicates that an entity is associated with an organized, armed group that operates similarly to a military force but is not part of the official state military.
-
D.
resistanceOrganization
Indicates an organization that actively opposes, resists, or fights against a dominant power, regime, or occupying force.
-
E.
armedGroup
Indicates that an entity is an organized group equipped with weapons and capable of using armed force.
- 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_69ca8284a25c8190a1a20afad30da792 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb14c336f08190a21a3fcaa7269457 |
completed | March 31, 2026, 12:26 a.m. |
| PD | Predicate disambiguation | batch_69cae91e98988190abd4ece75932c589 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:46 p.m.