Triple
T17557442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HAL (Hypertext Application Language) |
E427622
|
entity |
| Predicate | typicalMediaType |
P55167
|
FINISHED |
| Object | application/hal+json |
—
|
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: application/hal+json | Statement: [HAL (Hypertext Application Language), typicalMediaType, application/hal+json]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMediaType Context triple: [HAL (Hypertext Application Language), typicalMediaType, application/hal+json]
-
A.
typicalMIMEType
chosen
Indicates the standard or most commonly used MIME (media) type associated with a given resource or format.
-
B.
mediaType
Indicates the format or category of media associated with an entity, such as text, image, audio, or video.
-
C.
typicalFileType
Indicates that one entity is the usual or commonly associated file type for the other entity.
-
D.
mediaTypeAvailable
Indicates that a particular type or format of media is available for use, access, or distribution in the given context.
-
E.
ownedMediaType
Indicates the type or category of media content that is owned in the context of the ownership relationship.
- 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4562413d08190acaa5272046d3626 |
completed | April 19, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69e3b4fb39948190a82a597c5bac5c57 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:50 a.m.