Triple
T23477147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Porky's |
E570293
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Paul Zaza |
—
|
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: Paul Zaza | Statement: [Porky's, musicBy, Paul Zaza]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Zaza Context triple: [Porky's, musicBy, Paul Zaza]
-
A.
Paul Zaza
chosen
Paul Zaza is a Canadian film composer best known for his work on horror and genre films, including the score for "My Bloody Valentine."
-
B.
Arthur Zanetti
Arthur Zanetti is a Brazilian artistic gymnast renowned for his world and Olympic titles on the still rings.
-
C.
Michael Vincenzo Gazzo
Michael Vincenzo Gazzo was an American playwright and character actor best known for his Oscar-nominated role as Frank Pentangeli in "The Godfather Part II."
-
D.
Paul Mezzara
Paul Mezzara was a French art patron and textile manufacturer known for commissioning notable Art Nouveau works, including the Hôtel Mezzara in Paris.
-
E.
Cristian Zorzi
Cristian Zorzi is an Italian former cross-country skier best known for winning Olympic and World Championship medals, particularly as a sprint specialist and key member of Italy’s relay teams in the late 1990s and 2000s.
- 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a74dbea8819085ca84391039e7f7 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:01 p.m.