Triple
T4775464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dimitra Priebus |
E106033
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Dimitra Priebus |
E106033
|
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: Dimitra Priebus | Statement: [Dimitra Priebus, name, Dimitra Priebus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dimitra Priebus Context triple: [Dimitra Priebus, name, Dimitra Priebus]
-
A.
Dimitra Priebus
chosen
Dimitra Priebus is the mother of American attorney and former White House Chief of Staff Reince Priebus.
-
B.
Melania Knauss
Melania Knauss is a Slovenian-American former fashion model best known as the wife of Donald Trump and former First Lady of the United States.
-
C.
Barbara Müller
Barbara Müller was the wife of renowned German astronomer Johannes Kepler, with whom she shared a life during the early 17th century.
-
D.
Diana Villiers Negroponte
Diana Villiers Negroponte is a British-born lawyer, historian, and author known for her work on Latin American politics and U.S. foreign policy.
-
E.
Andrea Sperling
Andrea Sperling is an American film producer known for her work on independent and art-house films, including the acclaimed romantic drama "Like Crazy."
- 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_69bd43f3074c8190937e7b0a457fe9f1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6584481081908f1041a8827e0b42 |
completed | March 20, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43c6d7848190b998eee680149d6f |
completed | March 21, 2026, 7:07 a.m. |
Created at: March 20, 2026, 1:21 p.m.