Triple
T15390795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amy Dubanowski |
E368037
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Adam Dubanowski |
E1208945
|
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: Adam Dubanowski | Statement: [Amy Dubanowski, relative, Adam Dubanowski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Dubanowski Context triple: [Amy Dubanowski, relative, Adam Dubanowski]
-
A.
Adam Dubanowski
chosen
Adam Dubanowski is a character in the TV series "Unbreakable Kimmy Schmidt," known primarily as the husband of Amy Dubanowski.
-
B.
Dauber Dybinski
Dauber Dybinski is a dim-witted but good-hearted assistant coach character from the American sitcom "Coach."
-
C.
Adam Bielecki
Adam Bielecki is a Polish high-altitude mountaineer renowned for pioneering bold winter ascents in the Himalayas and Karakoram.
-
D.
Eric Dapkewicz
Eric Dapkewicz is a film editor best known for his work on major animated features, including DreamWorks Animation’s "Puss in Boots."
-
E.
Daniel Dubiecki
Daniel Dubiecki is an American film producer known for his work on acclaimed movies such as "Up in the Air" and other high-profile Hollywood 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_69d85a1551a08190ba2caea7cd51c639 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e7727a081908eff45bbc1633c8a |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0035450810819092796c556dfa8ed3 |
completed | May 10, 2026, 7:35 a.m. |
Created at: April 10, 2026, 3:19 a.m.