Triple
T202899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irin Carmon |
E4544
|
entity |
| Predicate | coAuthorWith |
P398
|
FINISHED |
| Object | Shana Knizhnik |
E7003
|
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: Shana Knizhnik | Statement: [Irin Carmon, coAuthorWith, Shana Knizhnik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shana Knizhnik Context triple: [Irin Carmon, coAuthorWith, Shana Knizhnik]
-
A.
Shana Knizhnik
chosen
Shana Knizhnik is an American lawyer, writer, and activist best known for co-creating the “Notorious RBG” meme and co-authoring the popular book about Supreme Court Justice Ruth Bader Ginsburg.
-
B.
Tania Chernova
Tania Chernova is a Soviet sniper and love interest of Vasily Zaitsev portrayed in the World War II film "Enemy at the Gates."
-
C.
Valeria Wasserman
Valeria Wasserman is a Brazilian linguist and translator best known as the wife of renowned intellectual Noam Chomsky.
-
D.
Marie Krackowizer
Marie Krackowizer was the wife of pioneering anthropologist Franz Boas and a supportive partner in his academic and intellectual life.
-
E.
Irina Korina
Irina Korina is the mother of late Russian-American actor Anton Yelchin.
- 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_69a25737567c81908f9c505300239181 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25be7337481909f4937fc1a06fb53 |
completed | Feb. 28, 2026, 3:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3949c6dfc81909a7aaa0ac3e91a65 |
completed | March 1, 2026, 1:21 a.m. |
Created at: Feb. 28, 2026, 2:51 a.m.