Triple
T6886708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrea del Verrocchio |
E158938
|
entity |
| Predicate | student |
P7251
|
FINISHED |
| Object | Perugino |
E124903
|
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: Perugino | Statement: [Andrea del Verrocchio, student, Perugino]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perugino Context triple: [Andrea del Verrocchio, student, Perugino]
-
A.
Perugino
chosen
Perugino was an Italian Renaissance painter renowned for his serene, harmonious compositions and as an important teacher and influence on Raphael.
-
B.
Pinturicchio
Pinturicchio was an Italian Renaissance painter known for his richly decorated frescoes in Rome and other Italian cities.
-
C.
Luca Signorelli
Luca Signorelli was an Italian Renaissance painter renowned for his powerful, anatomically precise frescoes and dramatic compositions, particularly in the Orvieto Cathedral.
-
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.
Carlo Dolci
Carlo Dolci was a 17th-century Italian Baroque painter from Florence, renowned for his highly finished, devout religious works and meticulous attention to detail.
- 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_69c688342f6c8190ad7eea6ba262db99 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d90e92488190b738676342ac6393 |
completed | March 27, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7584189008190b908f530a4525885 |
completed | March 28, 2026, 4:25 a.m. |
Created at: March 27, 2026, 2:23 p.m.