Triple
T1492167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SPARQL |
E29603
|
entity |
| Predicate | domain |
P87
|
FINISHED |
| Object | Linked Data |
E171295
|
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: Linked Data | Statement: [SPARQL, domain, Linked Data]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Linked Data Context triple: [SPARQL, domain, Linked Data]
-
A.
Linked Data
chosen
Linked Data is a method of publishing and interlinking structured data on the web using standard formats and URIs so that information can be easily connected and queried across different sources.
-
B.
Library of Congress Linked Data Service
The Library of Congress Linked Data Service is an online platform that publishes the Library of Congress’s controlled vocabularies and authority data in machine-readable linked data formats for use in cataloging and semantic web applications.
-
C.
Semantic Web
The Semantic Web is an extension of the current web in which information is given well-defined meaning through standards like RDF and OWL, enabling machines to understand, share, and reason about data across different systems.
-
D.
RDF
RDF (Resource Description Framework) is a standard model for data interchange on the Web that represents information as subject–predicate–object triples to enable structured, machine-readable metadata and knowledge graphs.
-
E.
JSON-LD
JSON-LD is a JSON-based format for encoding Linked Data, enabling structured data to be easily shared and understood across the web.
- 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_69a498dba1d8819093b46a3a8d2485f1 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c6c4f0c88190a97ba4910c1a5d85 |
completed | March 1, 2026, 11:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad232f4b80819095a608816d4d2a34 |
completed | March 8, 2026, 7:20 a.m. |
Created at: March 1, 2026, 8:12 p.m.