Triple
T13191624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biblioteka Imeni Lenina |
E314001
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | D. N. Chechulin |
E794192
|
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: D. N. Chechulin | Statement: [Biblioteka Imeni Lenina, architect, D. N. Chechulin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: D. N. Chechulin Context triple: [Biblioteka Imeni Lenina, architect, D. N. Chechulin]
-
A.
D. N. Chechulin
chosen
D. N. Chechulin was a prominent Soviet architect known for designing major public buildings and infrastructure projects in the USSR.
-
B.
V. Cheremin
V. Cheremin is an architect known for designing the Kuznetsky Most building.
-
C.
Nikolai Chagin
Nikolai Chagin was a Russian architect best known for designing the picturesque Church of the Resurrection of Christ in Foros, Crimea.
-
D.
Yuri V. Lonchakov
Yuri V. Lonchakov is a Russian cosmonaut and former Air Force pilot who flew multiple space missions, including long-duration stays on the International Space Station.
-
E.
V. B. Belogolovsky
V. B. Belogolovsky is an architect best known for his role in designing the Mask of Sorrow monument commemorating victims of political repression in Magadan, Russia.
- 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_69d806ae1e08819090d95bfe1538cc17 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c600ab48190bcf84aaf5846fb4b |
completed | April 10, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeb75ea708190a30153c76cde8e79 |
completed | May 10, 2026, 2:20 a.m. |
Created at: April 9, 2026, 9:15 p.m.