Triple
T21500553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Government House, Baku |
E530462
|
entity |
| Predicate | hasArchitect |
P184
|
FINISHED |
| Object |
K. Tkachenko
K. Tkachenko was an architect known for designing the prominent Government House building in Baku, Azerbaijan.
|
E1487760
|
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: K. Tkachenko | Statement: [Government House, Baku, hasArchitect, K. Tkachenko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: K. Tkachenko Context triple: [Government House, Baku, hasArchitect, K. Tkachenko]
-
A.
M. Klyavin
M. Klyavin is a structural engineer known for contributing to the design and stability of the Tallinn TV Tower in Estonia.
-
B.
Philip Zhmachenko
Philip Zhmachenko was a Soviet military commander and general who played a significant leadership role in Red Army operations during World War II.
-
C.
Oleg Ivenko
Oleg Ivenko is a Ukrainian ballet dancer and actor best known for portraying Rudolf Nureyev in the biographical film "The White Crow."
-
D.
Yuriy Kutsenko
Yuriy Kutsenko is a Russian actor known for his roles in both domestic films and international productions, including the science fiction thriller "The Darkest Hour."
-
E.
Leonid Kadenyuk
Leonid Kadenyuk was a Ukrainian cosmonaut and test pilot who became the first astronaut of independent Ukraine to fly in space.
- 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: K. Tkachenko Triple: [Government House, Baku, hasArchitect, K. Tkachenko]
Generated description
K. Tkachenko was an architect known for designing the prominent Government House building in Baku, Azerbaijan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: K. Tkachenko Target entity description: K. Tkachenko was an architect known for designing the prominent Government House building in Baku, Azerbaijan.
-
A.
M. Klyavin
M. Klyavin is a structural engineer known for contributing to the design and stability of the Tallinn TV Tower in Estonia.
-
B.
Philip Zhmachenko
Philip Zhmachenko was a Soviet military commander and general who played a significant leadership role in Red Army operations during World War II.
-
C.
Oleg Ivenko
Oleg Ivenko is a Ukrainian ballet dancer and actor best known for portraying Rudolf Nureyev in the biographical film "The White Crow."
-
D.
Yuriy Kutsenko
Yuriy Kutsenko is a Russian actor known for his roles in both domestic films and international productions, including the science fiction thriller "The Darkest Hour."
-
E.
Leonid Kadenyuk
Leonid Kadenyuk was a Ukrainian cosmonaut and test pilot who became the first astronaut of independent Ukraine to fly in space.
- 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_69e0c45bd15481909fba5910765cdda2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea5be400819093e2b7e145254eab |
completed | April 23, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09e13d6bc88190a55f46c68c9c55c2 |
completed | May 17, 2026, 3:39 p.m. |
| NEDg | Description generation | batch_6a09e1fc4f7881909e198768cdb43747 |
completed | May 17, 2026, 3:42 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09e2c86858819092216c12d8aa3348 |
completed | May 17, 2026, 3:46 p.m. |
Created at: April 16, 2026, 6:24 p.m.