Triple
T3988792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carnivàle |
E86936
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Amy Madigan |
E159006
|
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: Amy Madigan | Statement: [Carnivàle, starring, Amy Madigan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amy Madigan Context triple: [Carnivàle, starring, Amy Madigan]
-
A.
Amy Madigan
chosen
Amy Madigan is an American actress known for her Academy Award–nominated role in "Twice in a Lifetime" and performances in films such as "Field of Dreams" and "Uncle Buck."
-
B.
Pat Murphy
Pat Murphy is a name shared by several notable individuals, including an American science fiction and fantasy author and various sports figures.
-
C.
Frances Rafferty
Frances Rafferty was an American actress and dancer best known for her roles in 1940s MGM musicals and later in the television series "December Bride."
-
D.
Laura Leedy Gansler
Laura Leedy Gansler is an American lawyer and author best known for her nonfiction book about a landmark sexual harassment case that inspired the film "North Country."
-
E.
Janet Leahy
Janet Leahy is an American television writer and producer known for her work on acclaimed series such as Mad Men.
- 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_69aed93fd9d4819085d3b2137d2346cb |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa007344819099515fda367f7016 |
completed | March 9, 2026, 4:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5403235408190b47b8d4f4e21d094 |
completed | March 14, 2026, 11:02 a.m. |
Created at: March 9, 2026, 3:33 p.m.