Triple
T12211377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarov |
E290967
|
entity |
| Predicate | formerName |
P65
|
FINISHED |
| Object | Arzamas-75 |
E969083
|
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: Arzamas-75 | Statement: [Sarov, formerName, Arzamas-75]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arzamas-75 Context triple: [Sarov, formerName, Arzamas-75]
-
A.
Arzamas-16
chosen
Arzamas-16 was the secret Soviet closed city and primary nuclear weapons research center, now known as Sarov.
-
B.
Arzamas
Arzamas is a historic Russian city known for its religious architecture and cultural heritage, located in Nizhny Novgorod Oblast.
-
C.
Plesetsk
Plesetsk is a town in Arkhangelsk Oblast in northwestern Russia known primarily for its proximity to the Plesetsk Cosmodrome, a major Russian space launch facility.
-
D.
Novo-Ogaryovo
Novo-Ogaryovo is a suburban governmental estate outside Moscow that serves as one of the primary official residences of Russian President Vladimir Putin.
-
E.
Tula Arsenal
Tula Arsenal is a historic Russian arms manufacturer renowned for producing a wide range of military firearms, including iconic Soviet-era rifles.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91c915f548190b34a743f0a3bb51a |
completed | April 10, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e5666f48190a28eed761e7b9210 |
completed | May 2, 2026, 3:55 p.m. |
Created at: April 8, 2026, 9:51 p.m.