Triple
T13996245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | We Are Golden |
E336703
|
entity |
| Predicate | musicVideoDirector |
P4911
|
FINISHED |
| Object | Jonas Åkerlund |
E137269
|
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: Jonas Åkerlund | Statement: [We Are Golden, musicVideoDirector, Jonas Åkerlund]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jonas Åkerlund Context triple: [We Are Golden, musicVideoDirector, Jonas Åkerlund]
-
A.
Jonas Åkerlund
chosen
Jonas Åkerlund is a Swedish film and music video director known for his visually intense, fast-cut style in videos for major artists like Madonna, U2, and Lady Gaga.
-
B.
Tomas Alfredson
Tomas Alfredson is a Swedish film director best known internationally for his atmospheric, character-driven thrillers such as "Let the Right One In" and the espionage drama "Tinker Tailor Soldier Spy."
-
C.
Mark Romanek
Mark Romanek is an acclaimed American music video and film director known for his visually innovative work with artists like Nine Inch Nails, Madonna, and Johnny Cash, as well as for directing the feature film "One Hour Photo."
-
D.
Martin Arjovsky
Martin Arjovsky is a machine learning researcher best known for introducing the Wasserstein GAN, a generative adversarial network variant that improves training stability and sample quality.
-
E.
Matthew Hannam
Matthew Hannam is a Canadian film and television editor known for his work on acclaimed independent films and series.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2eb68ba88190bfaf10777d607bf3 |
completed | April 14, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbac9d4a54819091c7efbeb4dcc5f7 |
completed | May 6, 2026, 9:03 p.m. |
Created at: April 9, 2026, 10:19 p.m.