Triple
T8523703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mika Brzezinski |
E201758
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Ian Brzezinski |
E201759
|
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: Ian Brzezinski | Statement: [Mika Brzezinski, sibling, Ian Brzezinski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ian Brzezinski Context triple: [Mika Brzezinski, sibling, Ian Brzezinski]
-
A.
Ian Brzezinski
chosen
Ian Brzezinski is an American foreign policy and defense expert who has held senior roles in U.S. government and at prominent think tanks, particularly on NATO and European security issues.
-
B.
Peter Kornbluh
Peter Kornbluh is an American historian and investigative journalist known for his work on U.S. foreign policy and declassified government documents, particularly regarding Latin America.
-
C.
John Mark Deutch
John Mark Deutch is an American chemist, academic, and former government official who served as Director of Central Intelligence in the mid-1990s.
-
D.
David Kershenbaum
David Kershenbaum is an American record producer known for his work with prominent artists across folk, rock, and pop music since the 1970s.
-
E.
Bob Murawski
Bob Murawski is an American film editor best known for his work on movies such as "The Hurt Locker," for which he won an Academy Award.
- 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_69ca8321bb44819081b74df0b710276d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe64362c88190b978a2544eec6e3e |
completed | March 31, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf5139150081909a020db7ca4bccc3 |
completed | April 3, 2026, 5:33 a.m. |
Created at: March 30, 2026, 6:16 p.m.