Triple
T21814452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Connie Stevens |
E538563
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Concetta |
—
|
NE NERFINISHED |
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: Concetta | Statement: [Connie Stevens, givenName, Concetta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Concetta Context triple: [Connie Stevens, givenName, Concetta]
-
A.
Concetta
chosen
Concetta is a feminine given name of Italian origin, often associated with the singer Connie Francis (born Concetta Rosa Maria Franconero).
-
B.
Antonietta
Antonietta is a feminine given name, primarily used in Italian-speaking regions, that is a variant of the name Antoinette.
-
C.
Rosaria De Cicco
Rosaria De Cicco is an Italian actress known for her roles in contemporary Italian cinema and television comedies.
-
D.
Maria Rosaria
Maria Rosaria is the birth name of Italian politician and former television presenter Mara Carfagna.
-
E.
Pasqualina
Pasqualina is an Italian feminine given name, traditionally associated with the Easter period and used in various regions of Italy.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07cc8e6808190bde4d0e0981e4117 |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 16, 2026, 6:54 p.m.