Triple
T16306449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Heer |
E395926
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | “Vega: A Declarative Visualization Grammar” |
E1205482
|
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: “Vega: A Declarative Visualization Grammar” | Statement: [Jeff Heer, notableWork, “Vega: A Declarative Visualization Grammar”]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Vega: A Declarative Visualization Grammar” Context triple: [Jeff Heer, notableWork, “Vega: A Declarative Visualization Grammar”]
-
A.
Vega visualization grammar
chosen
Vega visualization grammar is a declarative language and toolkit for creating, sharing, and reproducing interactive data visualizations on the web.
-
B.
“A Tour through the Visualization Zoo”
“A Tour through the Visualization Zoo” is a widely cited survey article that systematically introduces and categorizes a broad range of data visualization techniques and design patterns.
-
C.
Protovis
Protovis is a declarative JavaScript toolkit for creating rich, interactive data visualizations in the web browser.
-
D.
Vega-Lite
Vega-Lite is a high-level grammar of interactive graphics that enables users to concisely create and share data visualizations, developed under the guidance of computer scientist Jeff Heer.
-
E.
The Craft of Information Visualization
The Craft of Information Visualization is a foundational book that compiles influential research papers and case studies on designing and evaluating effective visual representations of data and information.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288d5619081909d0f8157cc487877 |
completed | April 17, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00260151908190b83f700a1c7c6419 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:06 a.m.