Triple
T4497581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeffrey Tambor |
E100736
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Kasia Ostlun
Kasia Ostlun is the wife of American actor Jeffrey Tambor and the mother of several of his children.
|
E446398
|
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: Kasia Ostlun | Statement: [Jeffrey Tambor, spouse, Kasia Ostlun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kasia Ostlun Context triple: [Jeffrey Tambor, spouse, Kasia Ostlun]
-
A.
Aleksandra Dulkiewicz
Aleksandra Dulkiewicz is a Polish lawyer and politician who serves as the mayor of Gdańsk, known for her pro-European stance and advocacy of democratic values.
-
B.
Monika Jaruzelska
Monika Jaruzelska is a Polish journalist, writer, and former stylist, known both for her media work and as the daughter of Poland’s former communist leader Wojciech Jaruzelski.
-
C.
Elana Toruń
Elana Toruń is a Polish football club based in the city of Toruń.
-
D.
Ewelina Hańska
Ewelina Hańska was a Polish noblewoman best known as the longtime correspondent, muse, and eventually wife of French novelist Honoré de Balzac.
-
E.
Marta Kwiatkowska
Marta Kwiatkowska is a prominent computer scientist known for her contributions to probabilistic model checking and formal verification.
- 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: Kasia Ostlun Triple: [Jeffrey Tambor, spouse, Kasia Ostlun]
Generated description
Kasia Ostlun is the wife of American actor Jeffrey Tambor and the mother of several of his children.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kasia Ostlun Target entity description: Kasia Ostlun is the wife of American actor Jeffrey Tambor and the mother of several of his children.
-
A.
Aleksandra Dulkiewicz
Aleksandra Dulkiewicz is a Polish lawyer and politician who serves as the mayor of Gdańsk, known for her pro-European stance and advocacy of democratic values.
-
B.
Monika Jaruzelska
Monika Jaruzelska is a Polish journalist, writer, and former stylist, known both for her media work and as the daughter of Poland’s former communist leader Wojciech Jaruzelski.
-
C.
Elana Toruń
Elana Toruń is a Polish football club based in the city of Toruń.
-
D.
Ewelina Hańska
Ewelina Hańska was a Polish noblewoman best known as the longtime correspondent, muse, and eventually wife of French novelist Honoré de Balzac.
-
E.
Marta Kwiatkowska
Marta Kwiatkowska is a prominent computer scientist known for her contributions to probabilistic model checking and formal verification.
- 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_69bd43cdf15081909a4fa2585ff63b3e |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd56c065e88190934eb0b1632d79bb |
completed | March 20, 2026, 2:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bd67c7da888190a60bd738e53156ed |
completed | March 20, 2026, 3:29 p.m. |
| NEDg | Description generation | batch_69bd683417b08190bc4e08638a30c0ec |
completed | March 20, 2026, 3:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bd68b4681c8190abb170ccb054cd05 |
completed | March 20, 2026, 3:33 p.m. |
Created at: March 20, 2026, 1 p.m.