Triple
T11412769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Engels |
E270412
|
entity |
| Predicate | hasPreviousName |
P65
|
FINISHED |
| Object | Pokrovsk |
E774323
|
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: Pokrovsk | Statement: [Engels, hasPreviousName, Pokrovsk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pokrovsk Context triple: [Engels, hasPreviousName, Pokrovsk]
-
A.
Pokrovsk
chosen
Pokrovsk is the former name of the Russian city now known as Engels, located in Saratov Oblast on the Volga River.
-
B.
Pokrovsk
Pokrovsk is a city in eastern Ukraine that serves as an important industrial and transport hub within Donetsk Oblast.
-
C.
Rzhev
Rzhev is a historic town in western Russia known for its strategic location on the Volga River and as the site of major World War II battles.
-
D.
Pokrovskoye
Pokrovskoye is a rural Siberian village in Russia best known as the birthplace and early home of the mystic Grigori Rasputin.
-
E.
Vyazma
Vyazma is a historic town in Smolensk Oblast, western Russia, known for its strategic military significance, particularly during World War II.
- 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_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d801acd9bc81908a23b1b7b4e778d3 |
completed | April 9, 2026, 7:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5b855f0508190a2e57ef9407ddb1a |
completed | April 20, 2026, 5:23 a.m. |
Created at: April 8, 2026, 9:34 p.m.