Triple
T8170626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adriana Caselotti |
E190807
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Adriana |
E415371
|
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: Adriana | Statement: [Adriana Caselotti, givenName, Adriana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adriana Context triple: [Adriana Caselotti, givenName, Adriana]
-
A.
Adriana
chosen
Adriana is the given first name of Adrian Balboa, the fictional wife of boxer Rocky Balboa in the "Rocky" film series.
-
B.
Fabiola
Fabiola is a given name of Latin origin, historically associated with saints and European royalty.
-
C.
Rosita
Rosita is a shy but talented pig and devoted mother who becomes a standout performer in the animated musical film "Sing."
-
D.
Romina
Romina is an Italian-American actress and singer best known as half of the pop duo Al Bano & Romina Power.
-
E.
Rosaura
Rosaura is a central character in Laura Esquivel’s novel "Like Water for Chocolate," known as Tita’s sister and romantic rival within the story’s intense family and culinary drama.
- 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4803de688190960438aa059d163b |
completed | March 31, 2026, 4:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf5cfd588190b12ef9b5799ffd88 |
completed | April 1, 2026, 6:46 a.m. |
Created at: March 30, 2026, 5:39 p.m.