Triple
T6506575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | El Lissitzky |
E150023
|
entity |
| Predicate | patronymicName |
P7966
|
FINISHED |
| Object | Markovich |
E211777
|
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: Markovich | Statement: [El Lissitzky, patronymicName, Markovich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Markovich Context triple: [El Lissitzky, patronymicName, Markovich]
-
A.
Markovitch
chosen
Markovitch is the family name of Dora Maar, the French photographer and painter closely associated with Pablo Picasso and the Surrealist movement.
-
B.
Kimovich
Kimovich is the Russian patronymic derived from the given name "Kim," used as a middle name indicating "son of Kim."
-
C.
Moskovitch
Moskovitch is a surname, likely of Eastern European or Jewish origin, used as a variant spelling of "Moskovitz."
-
D.
Markus
Markus is the given first name of the renowned abstract expressionist painter Mark Rothko.
-
E.
Menzel
Menzel is the surname of Idina Menzel, the American actress and singer best known for her roles in Broadway musicals and the film "Frozen."
- 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_69c687ef291081909d437f035eef1cda |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6996818c881909d036f916da0efb5 |
completed | March 27, 2026, 2:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6cb4aa1708190aa58a5c40af56eb2 |
completed | March 27, 2026, 6:24 p.m. |
Created at: March 27, 2026, 1:43 p.m.