Triple
T12512528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rumen Radev |
E299114
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Georgi Radev
Georgi Radev is known as the son of Bulgarian President Rumen Radev.
|
E993587
|
NE FINISHED |
How this triple was built (4 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: Georgi Radev | Statement: [Rumen Radev, hasChild, Georgi Radev]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Georgi Radev Context triple: [Rumen Radev, hasChild, Georgi Radev]
-
A.
Rumen Radev
Rumen Radev is a Bulgarian politician and former Air Force commander who has served as the country's president since 2017.
-
B.
Dimităr Peshev
Dimităr Peshev was a Bulgarian politician and deputy speaker of parliament who played a key role in preventing the deportation of Bulgaria’s Jews during the Holocaust and was later imprisoned by the communist regime.
-
C.
Rosen Plevneliev
Rosen Plevneliev is a Bulgarian politician and businessman who served as President of Bulgaria from 2012 to 2017.
-
D.
Dragomir Anguelov
Dragomir Anguelov is a computer scientist known for his work in machine learning and computer vision, particularly in 3D perception and autonomous driving.
-
E.
Blagoi Popov
Blagoi Popov was a Bulgarian communist and one of the co-defendants in the 1933 Leipzig Trial following the Reichstag fire in Nazi Germany.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Georgi Radev Triple: [Rumen Radev, hasChild, Georgi Radev]
Generated description
Georgi Radev is known as the son of Bulgarian President Rumen Radev.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Georgi Radev Target entity description: Georgi Radev is known as the son of Bulgarian President Rumen Radev.
-
A.
Rumen Radev
Rumen Radev is a Bulgarian politician and former Air Force commander who has served as the country's president since 2017.
-
B.
Dimităr Peshev
Dimităr Peshev was a Bulgarian politician and deputy speaker of parliament who played a key role in preventing the deportation of Bulgaria’s Jews during the Holocaust and was later imprisoned by the communist regime.
-
C.
Rosen Plevneliev
Rosen Plevneliev is a Bulgarian politician and businessman who served as President of Bulgaria from 2012 to 2017.
-
D.
Dragomir Anguelov
Dragomir Anguelov is a computer scientist known for his work in machine learning and computer vision, particularly in 3D perception and autonomous driving.
-
E.
Blagoi Popov
Blagoi Popov was a Bulgarian communist and one of the co-defendants in the 1933 Leipzig Trial following the Reichstag fire in Nazi Germany.
- F. None of above. chosen
Provenance (5 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_69d6ada4cd388190ae3bbf83ff87057a |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d9541d6e508190a4992f328e077467 |
completed | April 10, 2026, 7:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65eac74608190a6f1941ed5a05212 |
completed | May 2, 2026, 8:29 p.m. |
| NEDg | Description generation | batch_69f65fadc97081908376913e390cfc3d |
completed | May 2, 2026, 8:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f660c3d914819097b57784889ca389 |
completed | May 2, 2026, 8:38 p.m. |
Created at: April 8, 2026, 9:57 p.m.