Triple
T9787929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joan Cusack |
E237534
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Cusack |
E783796
|
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: Cusack | Statement: [Joan Cusack, familyName, Cusack]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cusack Context triple: [Joan Cusack, familyName, Cusack]
-
A.
Cusack
chosen
Cusack is a surname most prominently associated with a family of American and Irish actors, including John, Joan, and Ann Cusack.
-
B.
Dick Cusack
Dick Cusack was an American actor, filmmaker, and advertising executive, best known as the patriarch of the Cusack acting family.
-
C.
Christopher Coogan
Christopher Coogan is one of the children of American actor Jackie Coogan, who was famous as a child star and later for his role as Uncle Fester on "The Addams Family."
-
D.
John Cusack
John Cusack is an American actor, screenwriter, and producer known for his roles in films like "Say Anything..." and "High Fidelity" and for his outspoken political activism.
-
E.
Pat Connaughton
Pat Connaughton is an American professional basketball player and former two-sport standout at Notre Dame who has played as a guard/forward in the NBA, notably for the Milwaukee Bucks.
- 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_69ca84da927881909bda80caecad6010 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda2131164819099e8644e40a3cab6 |
completed | April 1, 2026, 10:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1c427cb2c81909fce8e1958ab3282 |
completed | April 5, 2026, 2:08 a.m. |
Created at: March 30, 2026, 8:27 p.m.