Triple
T10696803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellena di Rosalba |
E252164
|
entity |
| Predicate | isFromWork |
P25740
|
FINISHED |
| Object | The Italian |
E48710
|
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: The Italian | Statement: [Ellena di Rosalba, isFromWork, The Italian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Italian Context triple: [Ellena di Rosalba, isFromWork, The Italian]
-
A.
The Italian
chosen
The Italian is a 1797 Gothic novel by Ann Radcliffe, renowned for its suspenseful plot, atmospheric settings, and exploration of religious and psychological themes.
-
B.
Italian
Italian refers to a person or cultural identity associated with Italy, its language, traditions, and national heritage.
-
C.
Milanese
Milanese is a Western Lombard dialect spoken primarily in and around the city of Milan in northern Italy.
-
D.
Piemontese
Piemontese is a Romance language spoken primarily in Italy’s Piedmont region, distinct from standard Italian and recognized for its own rich literary and cultural tradition.
-
E.
Cesanese
Cesanese is a red Italian wine grape variety, traditionally grown in the Lazio region, known for producing aromatic, medium-bodied wines with spicy and floral notes.
- 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_69d6aa5cbabc8190973e683950d89faf |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fd89390c8190969ab2b4a79d5818 |
completed | April 9, 2026, 1:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d998e447e0819098e839e9e121a21f |
completed | April 11, 2026, 12:42 a.m. |
Created at: April 8, 2026, 9:12 p.m.