Triple
T26522558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Supreme Ruler of Russia |
E669996
|
entity |
| Predicate | deFactoNature |
P2435
|
FINISHED |
| Object | dictatorial power |
—
|
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: dictatorial power | Statement: [Supreme Ruler of Russia, deFactoNature, dictatorial power]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deFactoNature Context triple: [Supreme Ruler of Russia, deFactoNature, dictatorial power]
-
A.
digitalNature
Indicates a relationship where something exists, operates, or is characterized primarily in a digital or computational form rather than a physical or analog one.
-
B.
covertNature
Indicates that the relationship or action is carried out in a hidden, secretive, or clandestine manner, not meant to be openly observed or acknowledged.
-
C.
hasNature
chosen
Indicates that something possesses, exhibits, or is characterized by a particular inherent quality, essence, or fundamental type.
-
D.
localNatureSite
Indicates that a location is designated as a natural site of local significance or interest.
-
E.
territorialNature
Indicates a tendency of an entity to defend or assert control over a specific area or domain against others.
- 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_69eeb31b6dcc8190b30632dc3928a0c0 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f613c35b5481909ef85d87d1604be9 |
completed | May 2, 2026, 3:09 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 1:29 a.m.