Triple
T22068749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Tortorella |
E545348
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | John Tortorella |
—
|
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: John Tortorella | Statement: [John Tortorella, name, John Tortorella]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Tortorella Context triple: [John Tortorella, name, John Tortorella]
-
A.
John Tortorella
chosen
John Tortorella is a veteran NHL coach known for his demanding, defense-first style, fiery personality, and a Stanley Cup championship with the Tampa Bay Lightning.
-
B.
Vic DiCara
Vic DiCara is an American hardcore punk musician and guitarist best known for his influential work in bands like Inside Out, Beyond, and 108.
-
C.
Tony Amonte
Tony Amonte is a former American professional ice hockey right winger best known for his NHL career with teams like the Chicago Blackhawks and his scoring prowess in the 1990s and early 2000s.
-
D.
Mike Piscitelli
Mike Piscitelli is a filmmaker and photographer known for his music videos, commercials, and visual collaborations with various artists.
-
E.
Mike Larocca
Mike Larocca is a film producer known for his work on acclaimed projects including the multiverse-themed movie "Everything Everywhere All at Once."
- 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_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12885fe04819092cdde142f91e147 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:27 p.m.