Triple
T17889773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dick |
E447283
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Teri Garr |
—
|
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: Teri Garr | Statement: [Dick, castMember, Teri Garr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Teri Garr Context triple: [Dick, castMember, Teri Garr]
-
A.
Teri Garr
chosen
Teri Garr is an American actress known for her versatile performances in films such as "Young Frankenstein," "Close Encounters of the Third Kind," and "Tootsie."
-
B.
Lisa Dillman
Lisa Dillman is an American playwright known for her contemporary stage works and as a notable alumna of the Playwrights Workshop.
-
C.
Jami Gertz
Jami Gertz is an American actress known for her roles in 1980s films and television series, including standout performances in movies like "The Lost Boys" and "Quicksilver."
-
D.
Nancy Kyes
Nancy Kyes is an American actress best known for her roles in John Carpenter films, including the original Halloween and Assault on Precinct 13.
-
E.
Danielle Kaye
Danielle Kaye is known as the spouse of British film director and music video creator Tony Kaye.
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d7828b481909b645fceb37a7ca3 |
completed | April 19, 2026, 9:16 a.m. |
Created at: April 10, 2026, 10:18 a.m.