Triple
T26704301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dmitry Shemyaka |
E673243
|
entity |
| Predicate | tookPowerIn |
P8145
|
FINISHED |
| Object | Moscow |
—
|
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: Moscow | Statement: [Dmitry Shemyaka, tookPowerIn, Moscow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tookPowerIn Context triple: [Dmitry Shemyaka, tookPowerIn, Moscow]
-
A.
cameToPowerIn
chosen
Indicates the time or context in which an entity assumed control, authority, or leadership over a group, organization, or territory.
-
B.
cameToPowerAfter
Indicates that one entity assumed authority or control following the rule or tenure of another entity.
-
C.
cameToPowerThrough
Indicates the manner or process by which an entity attained authority, leadership, or control, specifying how it rose to power.
-
D.
hadExecutivePowerIn
Indicates that an entity held executive authority or governing power within a specified organization, institution, or jurisdiction during a certain period.
-
E.
assignsExecutivePowerTo
Indicates that executive authority or decision-making power is formally granted from one entity 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_69eecda2b49c8190a6c481cfc4c07954 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6178209548190aa912801975c105f |
completed | May 2, 2026, 3:25 p.m. |
| PD | Predicate disambiguation | batch_69f60b8dfa0c8190864e1a940024d0a0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:33 a.m.