Triple
T25374766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | flag of Benin |
E633027
|
entity |
| Predicate | writingDirectionOfDesign |
P30236
|
FINISHED |
| Object | left-to-right from hoist to fly |
—
|
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: left-to-right from hoist to fly | Statement: [flag of Benin, writingDirectionOfDesign, left-to-right from hoist to fly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writingDirectionOfDesign Context triple: [flag of Benin, writingDirectionOfDesign, left-to-right from hoist to fly]
-
A.
directionalDesignation
chosen
Indicates a relationship where one entity is assigned or labeled with a specific directional orientation relative to another entity or reference frame.
-
B.
documentsDesignApproachOf
Indicates that one entity records or specifies the design approach used for another entity.
-
C.
designAspect
Indicates that one entity represents a particular design-related feature, characteristic, or consideration of another entity.
-
D.
designOutcome
Indicates the result, effect, or consequence produced by a particular design or design process.
-
E.
designDescription
Indicates that an entity has a textual explanation or summary of its design, structure, or intended configuration.
- 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_69e75a90c0dc819092f928b6ea0ecc72 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f55e591ffc8190aac5b03db15e45da |
completed | May 2, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f4683b34748190818428489a226124 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:38 p.m.