Triple
T23339625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heavy Metal (film) |
E591698
|
entity |
| Predicate | voiceCastMember |
P9616
|
FINISHED |
| Object | Joe Flaherty |
—
|
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: Joe Flaherty | Statement: [Heavy Metal (film), voiceCastMember, Joe Flaherty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Flaherty Context triple: [Heavy Metal (film), voiceCastMember, Joe Flaherty]
-
A.
Joe Flaherty
chosen
Joe Flaherty was a Canadian-American comedian and actor best known as an original cast member and writer on the sketch comedy series SCTV.
-
B.
Michael James Flaherty
Michael James Flaherty is a character connected to Pegeen Mike in J.M. Synge’s play "The Playboy of the Western World."
-
C.
Sean P. Leahy
Sean P. Leahy is a notable individual recognized for achievements significant enough to be associated with the surname Leahy.
-
D.
Kevin J. Leahy
Kevin J. Leahy is a scholar and author, best known for his work in archaeology and the study of early medieval metalwork in Britain.
-
E.
James M. Fitzgerald
James M. Fitzgerald was a United States federal judge from Alaska, recognized for his long judicial service and contributions to the federal court system.
- 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_69e25d20156c81908c5c53195bd9c738 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f198317f4c8190a557cacb86568d6c |
completed | April 29, 2026, 5:33 a.m. |
Created at: April 17, 2026, 5:18 p.m.