Triple
T24649189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alphabetic Presentation Forms |
E610198
|
entity |
| Predicate | compatibilityDecomposition |
P73433
|
FINISHED |
| Object | many characters decompose to standard Armenian letters |
—
|
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: many characters decompose to standard Armenian letters | Statement: [Alphabetic Presentation Forms, compatibilityDecomposition, many characters decompose to standard Armenian letters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compatibilityDecomposition Context triple: [Alphabetic Presentation Forms, compatibilityDecomposition, many characters decompose to standard Armenian letters]
-
A.
decomposesIn
Indicates that one entity breaks down or separates into another entity or set of entities as its components or products.
-
B.
hasDecomposition
chosen
Indicates that something can be broken down or separated into constituent parts, components, or simpler elements.
-
C.
decompositionType
Indicates the specific way in which a whole is broken down into its constituent parts or components.
-
D.
yieldsDecomposition
Indicates that one entity produces or results in a particular breakdown or decomposition of another entity.
-
E.
projectionCompatibility
Indicates that two or more projections (such as views, mappings, or representations) are mutually consistent and can be combined or used together without conflict.
- 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_69e2c4d350a481909170482bc2ce6af9 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d6ef33081908f5d36ba1ae5f473 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 2:33 a.m.