Triple
T22129133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | "Weird Al" Yankovic |
E546863
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Suzanne Krajewski |
—
|
NE NERFINISHED |
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: Suzanne Krajewski | Statement: ["Weird Al" Yankovic, spouse, Suzanne Krajewski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suzanne Krajewski Context triple: ["Weird Al" Yankovic, spouse, Suzanne Krajewski]
-
A.
Suzanne Krajewski
chosen
Suzanne Krajewski is an American woman best known as the longtime wife of parody musician "Weird Al" Yankovic.
-
B.
Suzanne Frank
Suzanne Frank is the private client for Peter Eisenman’s experimental House VI residence, a landmark of deconstructivist architecture.
-
C.
Suzanne Bresseau
Suzanne Bresseau was the French wife of renowned Egyptian writer and intellectual Taha Hussein, known for her supportive role in his life and work.
-
D.
Suzanne Buirgy
Suzanne Buirgy is a film producer known for her work on major animated features such as "Home" and other DreamWorks Animation projects.
-
E.
Suzanne Bernert
Suzanne Bernert is a German-born Indian actress known for her portrayals of prominent political figures in Indian films and television.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e39bf348190b541bfa16a7b71e0 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12983acfc81908013f66acb31f198 |
completed | April 28, 2026, 9:41 p.m. |
Created at: April 16, 2026, 8:32 p.m.