Triple
T10678973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naïve art |
E251692
|
entity |
| Predicate | notableArtist |
P601
|
FINISHED |
| Object | Niko Pirosmani |
E87233
|
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: Niko Pirosmani | Statement: [Naïve art, notableArtist, Niko Pirosmani]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Niko Pirosmani Context triple: [Naïve art, notableArtist, Niko Pirosmani]
-
A.
Niko Pirosmani
chosen
Niko Pirosmani was a self-taught Georgian primitivist painter renowned for his simple, expressive depictions of everyday life and folk culture.
-
B.
Biagio Rossetti
Biagio Rossetti was a pioneering Italian Renaissance architect and urban planner, renowned for transforming Ferrara into one of Europe’s first modern planned cities.
-
C.
Piero di Cosimo
Piero di Cosimo was an Italian Renaissance painter from Florence known for his imaginative mythological scenes, eccentric personality, and innovative use of color and atmosphere.
-
D.
Andrea Crivelli
Andrea Crivelli was an architect known for his work on the Hofkirche in Innsbruck, a significant Renaissance-era church in Austria.
-
E.
Sassetta
Sassetta is a small historic hill town in Tuscany, Italy, known for its medieval architecture, chestnut forests, and thermal springs.
- 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_69d6aa5bd7c08190a816e733b4045c23 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fb9684e48190b2786823723cde6c |
completed | April 9, 2026, 1:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98885abf88190b54ed9db779d3ff0 |
completed | April 10, 2026, 11:32 p.m. |
Created at: April 8, 2026, 9:10 p.m.