Triple
T11909673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gill Sans |
E283359
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Gill Sans Regular |
E283359
|
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: Gill Sans Regular | Statement: [Gill Sans, hasVariant, Gill Sans Regular]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gill Sans Regular Context triple: [Gill Sans, hasVariant, Gill Sans Regular]
-
A.
Gill Sans
chosen
Gill Sans is a widely used British humanist sans-serif typeface designed by Eric Gill, known for its clean, modern look and extensive use in signage and branding.
-
B.
Libre Baskerville
Libre Baskerville is an open-source, web-optimized serif typeface that adapts the classic Baskerville design for modern digital use.
-
C.
Avenir
Avenir is Buick’s top-tier luxury sub-brand and trim line, offering more premium materials, advanced features, and upscale styling than the brand’s standard models.
-
D.
Lato
Lato is a Polish surname most famously borne by Grzegorz Lato, a legendary Polish footballer and World Cup Golden Boot winner.
-
E.
Frutiger
Frutiger is a widely used humanist sans-serif typeface designed by Adrian Frutiger, known for its clarity and legibility in signage and print.
- 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_69d6ab2c07e88190ba13b0d21fd6cf33 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8e5278eb081909a7ecfe38beeeda9 |
completed | April 10, 2026, 11:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f49ce47d488190af7f832e7719a4ce |
completed | May 1, 2026, 12:30 p.m. |
Created at: April 8, 2026, 9:44 p.m.