Triple
T7423360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SHACL |
E171301
|
entity |
| Predicate | hasFeature |
P182
|
FINISHED |
| Object | SHACL-SPARQL extension |
E171301
|
NE 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: SHACL-SPARQL extension | Statement: [SHACL, hasFeature, SHACL-SPARQL extension]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SHACL-SPARQL extension Context triple: [SHACL, hasFeature, SHACL-SPARQL extension]
-
A.
SHACL
chosen
SHACL is a W3C standard language for validating RDF data against a set of constraints or shapes.
-
B.
SPARQL
SPARQL is a semantic query language and protocol used to retrieve and manipulate data stored in Resource Description Framework (RDF) format on the Semantic Web.
-
C.
OWL 2 functional-style syntax
OWL 2 functional-style syntax is a formal, logic-oriented textual notation for writing OWL 2 ontologies in a precise and machine-readable way.
-
D.
OWL 2 QL
OWL 2 QL is a lightweight profile of the Web Ontology Language designed to enable efficient query answering over large datasets using standard relational database technologies.
-
E.
OWL 2 Manchester syntax
OWL 2 Manchester syntax is a user-friendly, human-readable syntax for writing OWL 2 ontologies, designed to be easier to read and write than XML- or logic-based notations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c68a625d048190af70eb8b63bec5a0 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f2eece588190905774e7151edcb8 |
completed | March 27, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c81effc488819086336eea92604fa8 |
completed | March 28, 2026, 6:33 p.m. |
Created at: March 27, 2026, 3:12 p.m.