Triple
T31550822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homshetsi |
E804993
|
entity |
| Predicate | syntaxRelatedTo |
P95957
|
FINISHED |
| Object | Western Armenian syntax |
—
|
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: Western Armenian syntax | Statement: [Homshetsi, syntaxRelatedTo, Western Armenian syntax]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: syntaxRelatedTo Context triple: [Homshetsi, syntaxRelatedTo, Western Armenian syntax]
-
A.
syntaxBasedOn
Indicates that the syntactic structure or rules of one entity are derived from, influenced by, or constructed according to the syntax of another entity.
-
B.
semanticRelation
Indicates a general meaning-based connection between two entities, such as similarity, implication, or conceptual association.
-
C.
syntaxChangedIn
Indicates that the syntactic form or structure of something has been modified in a particular context, version, or point in time.
-
D.
linguisticallyRelatedTo
Indicates that two entities are connected through a linguistic relationship, such as sharing a common language, origin, structure, or other language-based association.
-
E.
hasSyntaxInfluenceFrom
chosen
Indicates that the syntax of one entity is influenced, shaped, or derived from the syntax of another entity.
- 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_69f348d11a048190a65eb8384a3754ac |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a8055f8081908f635fe04654b5fe |
completed | May 3, 2026, 1:42 a.m. |
| PD | Predicate disambiguation | batch_69f6a75656e081908739ed9e2f600e42 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 10:11 p.m.