Triple
T22489399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adobe Flex |
E555973
|
entity |
| Predicate | uses |
P98
|
FINISHED |
| Object | MXML |
—
|
NE NERFINISHED |
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: MXML | Statement: [Adobe Flex, uses, MXML]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MXML Context triple: [Adobe Flex, uses, MXML]
-
A.
MXML
chosen
MXML is an XML-based markup language used in Adobe Flex to define user interface layouts and application components for rich internet applications.
-
B.
Adobe Flex
Adobe Flex is a software development framework for building rich internet applications that run on the Adobe Flash platform using the ActionScript programming language.
-
C.
FXML
FXML is an XML-based markup language used to define the user interface of JavaFX applications separately from application logic.
-
D.
ActionScript
ActionScript is an object-oriented programming language primarily used for developing rich internet applications and Adobe Flash content.
-
E.
XAML
XAML is a declarative XML-based markup language used primarily for designing user interfaces in Microsoft .NET applications, especially on Windows.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e53897c819088863779f8c50bb0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15c3f3b4c819092bfe6495c61db46 |
completed | April 29, 2026, 1:17 a.m. |
Created at: April 16, 2026, 8:49 p.m.