Triple
T13753658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carla Tortelli |
E330418
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Ann Marie Tortelli |
E1098592
|
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: Ann Marie Tortelli | Statement: [Carla Tortelli, child, Ann Marie Tortelli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ann Marie Tortelli Context triple: [Carla Tortelli, child, Ann Marie Tortelli]
-
A.
Carla Tortelli
Carla Tortelli is a sharp-tongued, tough, and fiercely loyal waitress on the classic American sitcom "Cheers."
-
B.
Lucinda Tortelli
chosen
Lucinda Tortelli is one of Carla Tortelli’s children on the classic television sitcom "Cheers."
-
C.
Maria Pia Calzone
Maria Pia Calzone is an Italian actress known for her work in film and television, including prominent roles in contemporary Italian cinema and series.
-
D.
Concetta Tomei
Concetta Tomei is an American character actress known for her work in television, film, and theater, including prominent roles in series such as "China Beach."
-
E.
Donna Gigliotti
Donna Gigliotti is an Academy Award–winning American film producer known for acclaimed works such as "Shakespeare in Love" and "Silver Linings Playbook."
- 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_69d81c573f288190aa2403d484fa3d49 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0215cfa08190aaed8b089aff217b |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd6474da3081909be6b892ef8cc73e |
completed | May 8, 2026, 4:20 a.m. |
Created at: April 9, 2026, 10:09 p.m.