Triple
T14210099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kozlov |
E352204
|
entity |
| Predicate | usedInHistoricalDocuments |
P16500
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Kozlov, usedInHistoricalDocuments, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInHistoricalDocuments Context triple: [Kozlov, usedInHistoricalDocuments, yes]
-
A.
historicallyDocumentedBy
Indicates that information about an entity or event is recorded or attested in a specific historical document or source.
-
B.
hasHistoriographicalUse
chosen
Indicates that something is used or cited within historical writing or analysis as part of constructing, interpreting, or debating historical narratives.
-
C.
usedInOfficialDocumentsOf
Indicates that something (e.g., a term, symbol, or format) is employed within the formal or legally recognized documents issued by a particular entity or jurisdiction.
-
D.
historicUsePersistsIn
Indicates that a practice, feature, or condition originating in the past continues to exist or be applied in the present.
-
E.
historicallyUsedFor
Indicates that something served a particular function or purpose at some point in the past, even if it may no longer be used that way now.
- 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_69d8278a06e481908b5d6af0a8afe737 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61fa8d24819092a8ec5d34c1c799 |
completed | April 14, 2026, 3:49 p.m. |
| PD | Predicate disambiguation | batch_69de05bcd7d48190a4848d9320404aa6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 1:05 a.m.