Triple
T37290800
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mirs of Hunza |
E925659
|
entity |
| Predicate | maintainedForce |
P192533
|
FINISHED |
| Object | local militia |
—
|
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: local militia | Statement: [Mirs of Hunza, maintainedForce, local militia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintainedForce Context triple: [Mirs of Hunza, maintainedForce, local militia]
-
A.
maintainedFor
Indicates that something is kept in a particular state, condition, or operation for the benefit, use, or purpose of another entity.
-
B.
maintainedDespite
Indicates that a condition, relationship, or state continues to hold or remain in effect even though some opposing, challenging, or changing factor is present.
-
C.
soughtToMaintain
Indicates an entity’s deliberate effort or intention to keep another entity or condition in its existing state over time.
-
D.
maintainsThrough
Indicates that one entity preserves, upholds, or continues a state, condition, or relationship by means of another specified entity, process, or medium.
-
E.
hasMaintained
Indicates that an entity has continued to keep another entity in a particular state, condition, or relationship over a period of time.
- 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_69f76eb0f86c819098dee07393e69ec3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd0d0ba5c48190bddb3f0e6637544c |
completed | May 7, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69fd0c4324a8819086c90adf46216e0e |
completed | May 7, 2026, 10:03 p.m. |
| PDg | Predicate description generation | batch_69fd0d0aebac8190868a7714ddb4f1fd |
completed | May 7, 2026, 10:07 p.m. |
Created at: May 3, 2026, 4:16 p.m.