Triple
T23140246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beastly |
E577440
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Susan Cartsonis |
—
|
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: Susan Cartsonis | Statement: [Beastly, producer, Susan Cartsonis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Cartsonis Context triple: [Beastly, producer, Susan Cartsonis]
-
A.
Susan Cartsonis
chosen
Susan Cartsonis is an American film producer known for her work on popular studio movies, particularly romantic comedies and character-driven dramas.
-
B.
Denise Haratzis
Denise Haratzis is a film editor known for her work on the Australian romantic comedy-drama "Love Serenade."
-
C.
Lisa Katselas
Lisa Katselas is a film producer best known for her work on notable independent and art-house films in the 1990s.
-
D.
Lisa Mordente
Lisa Mordente is an American actress, singer, dancer, and choreographer known for her work on Broadway and in film and television.
-
E.
Jocelyn Carter
Jocelyn Carter is a principled and determined NYPD detective from the television series "Person of Interest," known for her moral integrity and pursuit of justice.
- 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_69e245f8e6248190ba3d58e068b4dccb |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ec922b481908084eee6a95aef83 |
completed | April 29, 2026, 4:53 a.m. |
Created at: April 17, 2026, 4 p.m.