Triple
T18861712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Last.fm |
E461326
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Martin Stiksel
Martin Stiksel is a tech entrepreneur best known as a co-founder of the music recommendation and streaming service Last.fm.
|
E1346644
|
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: Martin Stiksel | Statement: [Last.fm, foundedBy, Martin Stiksel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martin Stiksel Context triple: [Last.fm, foundedBy, Martin Stiksel]
-
A.
Martin Kosleck
Martin Kosleck was a German-American character actor best known for playing suave villains and Nazi antagonists in Hollywood films of the 1930s and 1940s.
-
B.
Martin Kitrosser
Martin Kitrosser is an American film industry professional best known for his work as a script supervisor and screenwriter on various genre and comedy films.
-
C.
Marc Sirkin
Marc Sirkin is a local political leader who serves as the mayor of Blue Ash, Ohio.
-
D.
Martin Straka
Martin Straka is a retired Czech professional ice hockey forward and Olympic gold medalist who enjoyed a long NHL career before becoming a prominent figure in Czech domestic hockey.
-
E.
John Kundla
John Kundla was a Hall of Fame American basketball coach best known for leading the Minneapolis Lakers to multiple early NBA championships.
- 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: Martin Stiksel Triple: [Last.fm, foundedBy, Martin Stiksel]
Generated description
Martin Stiksel is a tech entrepreneur best known as a co-founder of the music recommendation and streaming service Last.fm.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Martin Stiksel Target entity description: Martin Stiksel is a tech entrepreneur best known as a co-founder of the music recommendation and streaming service Last.fm.
-
A.
Martin Kosleck
Martin Kosleck was a German-American character actor best known for playing suave villains and Nazi antagonists in Hollywood films of the 1930s and 1940s.
-
B.
Martin Kitrosser
Martin Kitrosser is an American film industry professional best known for his work as a script supervisor and screenwriter on various genre and comedy films.
-
C.
Marc Sirkin
Marc Sirkin is a local political leader who serves as the mayor of Blue Ash, Ohio.
-
D.
Martin Straka
Martin Straka is a retired Czech professional ice hockey forward and Olympic gold medalist who enjoyed a long NHL career before becoming a prominent figure in Czech domestic hockey.
-
E.
John Kundla
John Kundla was a Hall of Fame American basketball coach best known for leading the Minneapolis Lakers to multiple early NBA championships.
- 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c06184d88190bd05413a07a8c9ce |
completed | April 20, 2026, 5:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0575b73f0c8190a04769515217c39c |
completed | May 14, 2026, 7:11 a.m. |
| NEDg | Description generation | batch_6a0576e3915c819098a969ddd2b2d1a5 |
completed | May 14, 2026, 7:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05777f51b481909a7916bc40dcfd69 |
completed | May 14, 2026, 7:19 a.m. |
Created at: April 10, 2026, 11:57 a.m.