Triple
T23845766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stalsk‑12 |
E591114
|
entity |
| Predicate | primaryAntagonistStrongholdOf |
P130722
|
FINISHED |
| Object | Andrei Sator |
—
|
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: Andrei Sator | Statement: [Stalsk‑12, primaryAntagonistStrongholdOf, Andrei Sator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryAntagonistStrongholdOf Context triple: [Stalsk‑12, primaryAntagonistStrongholdOf, Andrei Sator]
-
A.
antagonistBaseOf
chosen
Indicates that one entity serves as the primary base, headquarters, or stronghold from which an antagonist operates or exerts influence over another entity.
-
B.
primaryAntagonistType
Indicates the role or category of the main opposing force or adversary that serves as the central source of conflict.
-
C.
primaryAntagonists
Indicates that the referenced entities serve as the main opposing or adversarial forces in relation to a specified subject or narrative.
-
D.
primaryAntagonisticRealmIn
Indicates that an entity’s main or most significant antagonistic or opposing activity occurs within a specified realm or domain.
-
E.
antagonistOf
Indicates a relationship where one entity actively opposes, conflicts with, or serves as an adversary to another.
- 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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c88b59688190922d6bf329f08721 |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:09 p.m.