Triple
T12718427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mariss Jansons |
E303909
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object |
Iraida Jansone
Iraida Jansone was the mother of renowned Latvian conductor Mariss Jansons.
|
E999684
|
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: Iraida Jansone | Statement: [Mariss Jansons, mother, Iraida Jansone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Iraida Jansone Context triple: [Mariss Jansons, mother, Iraida Jansone]
-
A.
Anna-Marija Slotiņa
Anna-Marija Slotiņa is a Latvian actress and former model best known publicly as the wife of Chilean-British actor Santiago Cabrera.
-
B.
Jolanta Umecka
Jolanta Umecka is a Polish actress best known for her role in Roman Polanski’s 1962 psychological drama film "Knife in the Water."
-
C.
Jurgita Dronina
Jurgita Dronina is a Lithuanian-Canadian ballerina acclaimed internationally as a principal dancer for her virtuosity, dramatic artistry, and leading roles with major ballet companies.
-
D.
Anfisa Vistingauzen
Anfisa Vistingauzen is a Russian actress known for her roles in film and television, including the thriller "Metro."
-
E.
Varvara Andreevna Zmuidzinas
Varvara Andreevna Zmuidzinas, better known as Karinska, was a renowned costume designer celebrated for her influential work in ballet and theater, particularly with the New York City Ballet.
- 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: Iraida Jansone Triple: [Mariss Jansons, mother, Iraida Jansone]
Generated description
Iraida Jansone was the mother of renowned Latvian conductor Mariss Jansons.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Iraida Jansone Target entity description: Iraida Jansone was the mother of renowned Latvian conductor Mariss Jansons.
-
A.
Anna-Marija Slotiņa
Anna-Marija Slotiņa is a Latvian actress and former model best known publicly as the wife of Chilean-British actor Santiago Cabrera.
-
B.
Jolanta Umecka
Jolanta Umecka is a Polish actress best known for her role in Roman Polanski’s 1962 psychological drama film "Knife in the Water."
-
C.
Jurgita Dronina
Jurgita Dronina is a Lithuanian-Canadian ballerina acclaimed internationally as a principal dancer for her virtuosity, dramatic artistry, and leading roles with major ballet companies.
-
D.
Anfisa Vistingauzen
Anfisa Vistingauzen is a Russian actress known for her roles in film and television, including the thriller "Metro."
-
E.
Varvara Andreevna Zmuidzinas
Varvara Andreevna Zmuidzinas, better known as Karinska, was a renowned costume designer celebrated for her influential work in ballet and theater, particularly with the New York City Ballet.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9625d9da48190ab377f9328a0e1f5 |
completed | April 10, 2026, 8:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67c802e248190865a6561ad1bf0b6 |
completed | May 2, 2026, 10:36 p.m. |
| NEDg | Description generation | batch_69f67d64ed3481908d434c20796866f9 |
completed | May 2, 2026, 10:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f67e82e35081909c4b5fad7e941610 |
completed | May 2, 2026, 10:45 p.m. |
Created at: April 9, 2026, 5:23 p.m.