Triple
T22813221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | @sveltejs/adapter-static |
E565035
|
entity |
| Predicate | typicalOutputDirectory |
P84816
|
FINISHED |
| Object | build |
—
|
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: build | Statement: [@sveltejs/adapter-static, typicalOutputDirectory, build]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalOutputDirectory Context triple: [@sveltejs/adapter-static, typicalOutputDirectory, build]
-
A.
outputOf
Indicates that one entity is the result or product generated by the processing, operation, or behavior of another entity.
-
B.
repositoryDirectoryName
Indicates the name assigned to the directory in which a repository is stored or organized.
-
C.
standardOutput
Indicates that one entity produces data or results that are directed to another entity’s standard output stream.
-
D.
outputsTo
chosen
Indicates that the result or data produced by one entity is directed or sent to another entity as its destination or target.
-
E.
outputConfiguration
Indicates how the results or data produced by a process, system, or component are structured, formatted, or directed to their destination.
- 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_69e2458426188190b58b8ab4844fe420 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17d61c6f081908d3911710b3aff51 |
completed | April 29, 2026, 3:39 a.m. |
| PD | Predicate disambiguation | batch_69eed2cb30f481909566369f515f6eff |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:32 p.m.