Triple
T14896015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Olonets Karelian |
E359876
|
entity |
| Predicate | hasCaseSystemSimilarTo |
P70832
|
FINISHED |
| Object | Finnish case system |
—
|
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: Finnish case system | Statement: [Olonets Karelian, hasCaseSystemSimilarTo, Finnish case system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCaseSystemSimilarTo Context triple: [Olonets Karelian, hasCaseSystemSimilarTo, Finnish case system]
-
A.
hasSimilarityTo
Indicates that one entity shares common characteristics, features, or qualities with another entity to a notable degree.
-
B.
namedForSimilarityTo
Indicates that one entity is given its name because of a perceived resemblance or likeness to another entity.
-
C.
hasCaseInflection
Indicates that a word or phrase changes form to reflect grammatical case (such as nominative, accusative, etc.) in a given language context.
-
D.
usesSameSystemAs
chosen
Indicates that two entities operate within or rely on the same underlying system, platform, or infrastructure.
-
E.
hasLetterSetSimilarity
Indicates that two entities share a similar set of letters, typically based on overlap or resemblance between the characters in their textual representations.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded6070b248190be8f4f91a0c0b1f3 |
completed | April 15, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69de9a4a14a88190951bb8f4c60bd37b |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:10 a.m.