Triple
T9727728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kurt Johnstad |
E235657
|
entity |
| Predicate | wroteScreenplayFor |
P15305
|
FINISHED |
| Object | Atomic Blonde |
E50476
|
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: Atomic Blonde | Statement: [Kurt Johnstad, wroteScreenplayFor, Atomic Blonde]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Atomic Blonde Context triple: [Kurt Johnstad, wroteScreenplayFor, Atomic Blonde]
-
A.
Atomic Blonde
chosen
Atomic Blonde is a 2017 action spy thriller film starring Charlize Theron as a lethal MI6 agent navigating espionage and betrayal in Cold War–era Berlin.
-
B.
Blonde
Blonde is a 2007 pop album by French singer Alizée that marked a stylistic evolution in her music career.
-
C.
Blonde
Blonde is Frank Ocean’s critically acclaimed 2016 studio album that blends R&B, avant-pop, and introspective songwriting.
-
D.
Blonde
Blonde is a 2022 psychological drama film written and directed by Andrew Dominik, loosely adapting Joyce Carol Oates’s novel to present a fictionalized, impressionistic portrayal of Marilyn Monroe’s life and career.
-
E.
Blonded
Blonded is Frank Ocean’s independent music label and creative platform used to release his work and related 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_69ca84d0fad481909cdd45aa77416c48 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e7af544819090a8a1adec41943c |
completed | April 1, 2026, 10:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1afba5ec081908044a4aefdc6f9ee |
completed | April 5, 2026, 12:41 a.m. |
Created at: March 30, 2026, 8:21 p.m.