Triple
T2850824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander Bernstein |
E63086
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Nina Bernstein |
E138053
|
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: Nina Bernstein | Statement: [Alexander Bernstein, sibling, Nina Bernstein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nina Bernstein Context triple: [Alexander Bernstein, sibling, Nina Bernstein]
-
A.
Nina Bernstein
chosen
Nina Bernstein is the daughter of renowned American composer and conductor Leonard Bernstein, known for helping preserve and promote her father's musical legacy.
-
B.
Nina Bushkin
Nina Bushkin was the wife of renowned American lyricist and playwright Alan Jay Lerner.
-
C.
Nina Loeb
Nina Loeb was an American socialite and member of the prominent Loeb banking family who married financier and Federal Reserve pioneer Paul Warburg.
-
D.
Tatiana Schlossberg
Tatiana Schlossberg is an American journalist and author, known for her environmental reporting and as a member of the Kennedy family.
-
E.
Juliana Minsky
Juliana Minsky is a daughter of pioneering artificial intelligence researcher Marvin Minsky.
- 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_69ab4c407c408190857d25e027155ce9 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf437328819098506ec8a3a23e11 |
completed | March 7, 2026, 8:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2249f50008190921040166f6036b9 |
completed | March 12, 2026, 2:27 a.m. |
Created at: March 6, 2026, 10:02 p.m.