Triple
T3621758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Funny or Die |
E76742
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Michael Kvamme |
E372964
|
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: Michael Kvamme | Statement: [Funny or Die, foundedBy, Michael Kvamme]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Kvamme Context triple: [Funny or Die, foundedBy, Michael Kvamme]
-
A.
Mark Kvamme
chosen
Mark Kvamme is an American venture capitalist and entrepreneur known for co-founding the comedy video website Funny or Die and for his prominent role at the venture capital firm Sequoia Capital.
-
B.
Christian M. Ravndal
Christian M. Ravndal was an American diplomat who served as the United States Ambassador to Hungary.
-
C.
Ralph Høibakk
Ralph Høibakk is a Norwegian mountaineer and engineer known for his pioneering high-altitude climbs, including the first ascent of the Himalayan peak Tirich Mir.
-
D.
Tim Lovestedt
Tim Lovestedt is a screenwriter known for his work on the military drama film "Megan Leavey."
-
E.
Erik Selvig
Erik Selvig is a fictional astrophysicist in the Marvel Cinematic Universe who becomes a close ally of Thor and plays a key role in studying and understanding cosmic phenomena.
- 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2bb12cc8190bd67597cf3b66a3a |
completed | March 8, 2026, 6:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b44f0e8d1c8190ae1728d07d5a9e87 |
completed | March 13, 2026, 5:53 p.m. |
Created at: March 8, 2026, 3:23 p.m.