Triple
T9920099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Chapman |
E185971
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object | Lionel Fusco |
E407858
|
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: Lionel Fusco | Statement: [Kevin Chapman, portrayed, Lionel Fusco]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lionel Fusco Context triple: [Kevin Chapman, portrayed, Lionel Fusco]
-
A.
Lionel Fusco
chosen
Lionel Fusco is a central character in the TV series "Person of Interest," a once-corrupt NYPD detective who becomes a loyal ally to the show's protagonists.
-
B.
Louis De Francesco
Louis De Francesco was a film composer best known for scoring the 1933 drama "The Power and the Glory."
-
C.
Rene Tosoni
Rene Tosoni is a Canadian former professional baseball outfielder who played in Major League Baseball for the Minnesota Twins.
-
D.
Louis Cioffi
Louis Cioffi is a film editor known for his work on feature films, including the crime drama "Wonderland" (2003).
-
E.
Jean Leonetti
Jean Leonetti is a French politician and physician known for his work on end-of-life legislation and his long-standing role in center-right national politics.
- 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_69ca829b45f481909040f7b99a1976ed |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb5699bc48190961e036d1131fef0 |
completed | April 2, 2026, 12:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d228b8974c81909a603407ebe3df1f |
completed | April 5, 2026, 9:17 a.m. |
Created at: March 30, 2026, 8:42 p.m.