Triple
T22092441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dead Man Down |
E545943
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object |
Jacob Groth
Jacob Groth is a Danish film composer best known for his atmospheric scores for Nordic crime dramas and international thrillers.
|
E1519186
|
NE FINISHED |
How this triple was built (4 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: Jacob Groth | Statement: [Dead Man Down, musicBy, Jacob Groth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jacob Groth Context triple: [Dead Man Down, musicBy, Jacob Groth]
-
A.
Christian Groth
Christian Groth is a Danish economist known for his contributions to macroeconomic theory, particularly in the areas of growth and development economics.
-
B.
Holger Rune
Holger Rune is a Danish professional tennis player known for his powerful baseline game and rapid rise into the sport’s top ranks.
-
C.
Jannik Tai Mosholt
Jannik Tai Mosholt is a Danish screenwriter and producer best known for co-creating and writing the post-apocalyptic Netflix series "The Rain."
-
D.
Viktor Axelsen
Viktor Axelsen is a Danish badminton player renowned as one of the world’s leading men’s singles competitors and an Olympic gold medalist.
-
E.
Lars Markgren
Lars Markgren is a co-founder of King Digital Entertainment, the company best known for creating the popular mobile game Candy Crush Saga.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Jacob Groth Triple: [Dead Man Down, musicBy, Jacob Groth]
Generated description
Jacob Groth is a Danish film composer best known for his atmospheric scores for Nordic crime dramas and international thrillers.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jacob Groth Target entity description: Jacob Groth is a Danish film composer best known for his atmospheric scores for Nordic crime dramas and international thrillers.
-
A.
Christian Groth
Christian Groth is a Danish economist known for his contributions to macroeconomic theory, particularly in the areas of growth and development economics.
-
B.
Holger Rune
Holger Rune is a Danish professional tennis player known for his powerful baseline game and rapid rise into the sport’s top ranks.
-
C.
Jannik Tai Mosholt
Jannik Tai Mosholt is a Danish screenwriter and producer best known for co-creating and writing the post-apocalyptic Netflix series "The Rain."
-
D.
Viktor Axelsen
Viktor Axelsen is a Danish badminton player renowned as one of the world’s leading men’s singles competitors and an Olympic gold medalist.
-
E.
Lars Markgren
Lars Markgren is a co-founder of King Digital Entertainment, the company best known for creating the popular mobile game Candy Crush Saga.
- F. None of above. chosen
Provenance (5 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_69e11e36d03c8190a83a1ba802b7231b |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128e6b1d881909bf0f4a52199354c |
completed | April 28, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a879b9130819089f8e2b7106f875b |
completed | May 18, 2026, 3:29 a.m. |
| NEDg | Description generation | batch_6a0a891eb0708190a4575a01f45b98aa |
completed | May 18, 2026, 3:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a89977c8c8190a5c87d1c2b68ed48 |
completed | May 18, 2026, 3:37 a.m. |
Created at: April 16, 2026, 8:29 p.m.