Triple
T14521022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark Waters |
E340650
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Pam Koffler |
E445582
|
NE FINISHED |
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: Pam Koffler | Statement: [Dark Waters, producer, Pam Koffler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pam Koffler Context triple: [Dark Waters, producer, Pam Koffler]
-
A.
Pam Koffler
chosen
Pam Koffler is an American film producer and co-founder of the independent production company Killer Films, known for acclaimed art-house and LGBTQ-themed cinema.
-
B.
Linda Voss
Linda Voss is the courageous American legal secretary-turned-spy who infiltrates Nazi Germany in the World War II espionage drama "Shining Through."
-
C.
Nancy Shevell
Nancy Shevell is an American businesswoman and heiress best known for her long-term relationship and marriage to musician Paul McCartney.
-
D.
Donna Ehlert
Donna Ehlert is best known as the first wife of American comedic actor Harvey Korman.
-
E.
Gail Helfrich
Gail Helfrich is known as the wife of American football coach Mark Helfrich, who notably served as head coach of the University of Oregon Ducks.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d822d9c0408190b9a2b3643e58bb4d |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69de9a72cff08190878b4bed9b0b5eb5 |
completed | April 14, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9db810c481908dde925ff90f3fa0 |
completed | May 9, 2026, 2:36 a.m. |
Created at: April 10, 2026, 1:22 a.m.