Triple
T10226236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | True Crime |
E243210
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Paul Brickman |
E364041
|
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: Paul Brickman | Statement: [True Crime, screenwriter, Paul Brickman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Brickman Context triple: [True Crime, screenwriter, Paul Brickman]
-
A.
Paul Brickman
chosen
Paul Brickman is an American filmmaker and screenwriter best known for writing and directing the 1983 coming-of-age film "Risky Business."
-
B.
Michael Brickler
Michael Brickler is an entrepreneur best known as a co-founder of the architecture and design firm Morphosis.
-
C.
Dennis Marks
Dennis Marks is a name shared by several notable individuals, including an American television producer and writer and a British opera director and translator.
-
D.
Paul Colichman
Paul Colichman is an American film and television producer and media executive best known for his work on independent and LGBTQ-themed projects and for co-founding the Here Media network.
-
E.
Barry Kramer
Barry Kramer is an American video editor and internet personality best known for his work on the Game Grumps YouTube channel and related online projects.
- 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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d1f9cf6c81909a6b9e9b9d0a79fe |
completed | April 7, 2026, 9:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f71fb4048190a36f1fe499729332 |
completed | April 9, 2026, 12:47 a.m. |
Created at: April 6, 2026, 11:17 a.m.