Triple
T1030201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jawed Karim |
E22231
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object |
Christine Karim
Christine Karim is the mother of YouTube co-founder Jawed Karim.
|
E155454
|
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: Christine Karim | Statement: [Jawed Karim, parent, Christine Karim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Christine Karim Context triple: [Jawed Karim, parent, Christine Karim]
-
A.
Christine Mara
Christine Mara is a member of the Mara family, known for its long-time ownership and leadership of the New York Giants NFL franchise.
-
B.
Jessica Szohr
Jessica Szohr is an American actress best known for her role as Vanessa Abrams on the television series "Gossip Girl" and later as a main cast member on the sci-fi comedy-drama "The Orville."
-
C.
Lara Lea Yunaska
Lara Lea Yunaska is an American television producer and political figure best known as Lara Trump, the wife of Eric Trump and a prominent surrogate and adviser in Donald Trump’s political campaigns.
-
D.
Jayne-Ann Tenggren
Jayne-Ann Tenggren is a film producer best known for her work on the acclaimed World War I drama "1917."
-
E.
Kristen Tomassi
Kristen Tomassi is an American architect and designer best known as the first wife of British entrepreneur Richard Branson.
- 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: Christine Karim Triple: [Jawed Karim, parent, Christine Karim]
Generated description
Christine Karim is the mother of YouTube co-founder Jawed Karim.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Christine Karim Target entity description: Christine Karim is the mother of YouTube co-founder Jawed Karim.
-
A.
Christine Mara
Christine Mara is a member of the Mara family, known for its long-time ownership and leadership of the New York Giants NFL franchise.
-
B.
Jessica Szohr
Jessica Szohr is an American actress best known for her role as Vanessa Abrams on the television series "Gossip Girl" and later as a main cast member on the sci-fi comedy-drama "The Orville."
-
C.
Lara Lea Yunaska
Lara Lea Yunaska is an American television producer and political figure best known as Lara Trump, the wife of Eric Trump and a prominent surrogate and adviser in Donald Trump’s political campaigns.
-
D.
Jayne-Ann Tenggren
Jayne-Ann Tenggren is a film producer best known for her work on the acclaimed World War I drama "1917."
-
E.
Kristen Tomassi
Kristen Tomassi is an American architect and designer best known as the first wife of British entrepreneur Richard Branson.
- 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_69a493d848848190aed4011b34b2e8d3 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7f962608190b3ebd9140472b979 |
completed | March 1, 2026, 10:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acce53fd1c81909b3715231ad09b91 |
completed | March 8, 2026, 1:18 a.m. |
| NEDg | Description generation | batch_69accef1f294819093f463001ae8796b |
completed | March 8, 2026, 1:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69accf59a4e48190bfe11b97c4d33913 |
completed | March 8, 2026, 1:22 a.m. |
Created at: March 1, 2026, 7:41 p.m.