Triple
T2140111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dermot Mulroney |
E46740
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Tharita Cesaroni
Tharita Cesaroni is an Italian film producer and cinematographer known for her work behind the camera and for being married to actor Dermot Mulroney.
|
E248425
|
NE FINISHED |
How this triple was built (4 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: Tharita Cesaroni | Statement: [Dermot Mulroney, spouse, Tharita Cesaroni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tharita Cesaroni Context triple: [Dermot Mulroney, spouse, Tharita Cesaroni]
-
A.
Andrea Dotti
Andrea Dotti was an Italian psychiatrist best known for being the second husband of actress Audrey Hepburn.
-
B.
Angelica Galante
Angelica Galante was the mother of the renowned Italian Baroque sculptor and architect Gian Lorenzo Bernini.
-
C.
Francesca Cornelli
Francesca Cornelli is an Italian economist and academic leader known for her research in corporate finance and for serving as dean of Northwestern University's Kellogg School of Management.
-
D.
Lilia Vetti
Lilia Vetti was the wife of famed French singer and actor Tino Rossi.
-
E.
Natalina Garaventa
Natalina Garaventa was the Italian-born mother of American singer and actor Frank Sinatra, known for her strong personality and influence on his early life.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tharita Cesaroni Triple: [Dermot Mulroney, spouse, Tharita Cesaroni]
Generated description
Tharita Cesaroni is an Italian film producer and cinematographer known for her work behind the camera and for being married to actor Dermot Mulroney.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tharita Cesaroni Target entity description: Tharita Cesaroni is an Italian film producer and cinematographer known for her work behind the camera and for being married to actor Dermot Mulroney.
-
A.
Andrea Dotti
Andrea Dotti was an Italian psychiatrist best known for being the second husband of actress Audrey Hepburn.
-
B.
Angelica Galante
Angelica Galante was the mother of the renowned Italian Baroque sculptor and architect Gian Lorenzo Bernini.
-
C.
Francesca Cornelli
Francesca Cornelli is an Italian economist and academic leader known for her research in corporate finance and for serving as dean of Northwestern University's Kellogg School of Management.
-
D.
Lilia Vetti
Lilia Vetti was the wife of famed French singer and actor Tino Rossi.
-
E.
Natalina Garaventa
Natalina Garaventa was the Italian-born mother of American singer and actor Frank Sinatra, known for her strong personality and influence on his early life.
- F. None of above. chosen
Provenance (5 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbe04135c8190ab100b4b3879cb01 |
completed | March 7, 2026, 5:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae6aee10b08190abeb6059d4d2ad0a |
completed | March 9, 2026, 6:38 a.m. |
| NEDg | Description generation | batch_69ae6c3a69548190a04cdd492c537fd0 |
completed | March 9, 2026, 6:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae6cd61e808190aefca4d4aa1f8e39 |
completed | March 9, 2026, 6:46 a.m. |
Created at: March 4, 2026, 7:44 p.m.