Triple
T17829942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christine Vachon |
E445223
|
entity |
| Predicate | hasCollaboratedWith |
P8554
|
FINISHED |
| Object | Tom Kalin |
—
|
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: Tom Kalin | Statement: [Christine Vachon, hasCollaboratedWith, Tom Kalin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Kalin Context triple: [Christine Vachon, hasCollaboratedWith, Tom Kalin]
-
A.
Tom Kalin
chosen
Tom Kalin is an American filmmaker and screenwriter known for his pioneering work in New Queer Cinema, particularly the influential films "Swoon" and "Savage Grace."
-
B.
Michael Nolin
Michael Nolin is an American film producer best known for his work on the acclaimed music drama "Mr. Holland's Opus."
-
C.
Matt Kallman
Matt Kallman is an American keyboardist best known for his work with the indie rock band Real Estate and previously with Girls.
-
D.
Tom Jeter
Tom Jeter is a fictional sketch-comedy performer and writer from the television series "Studio 60 on the Sunset Strip."
-
E.
Greg DePaul
Greg DePaul is an American screenwriter and playwright best known for co-writing the romantic comedy film "Bride Wars."
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48917c4d88190b919a4b75aed011c |
completed | April 19, 2026, 7:49 a.m. |
Created at: April 10, 2026, 10:15 a.m.