Triple
T5224073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ganina Yama |
E117940
|
entity |
| Predicate | nearbySite |
P350
|
FINISHED |
| Object |
Porosenkov Log
Porosenkov Log is a forested area near Yekaterinburg, Russia, known as one of the sites associated with the execution and secret burial of the last Russian imperial family, the Romanovs.
|
E503104
|
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: Porosenkov Log | Statement: [Ganina Yama, nearbySite, Porosenkov Log]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porosenkov Log Context triple: [Ganina Yama, nearbySite, Porosenkov Log]
-
A.
Oreshek
Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
-
B.
Kologriv
Kologriv is a small historic town in Kostroma Oblast, Russia, known for its traditional wooden architecture and location within a forested, sparsely populated region.
-
C.
Khovrino
Khovrino is a Moscow Metro station serving as the northern terminus of the Zamoskvoretskaya Line.
-
D.
Sergiyev
Sergiyev is the former name of the Russian town now known as Sergiyev Posad, a historic center of Orthodox Christianity northeast of Moscow.
-
E.
Vyazemsky
Vyazemsky is a small town in Russia’s Far Eastern Federal District, serving as an administrative center within Khabarovsk Krai.
- 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: Porosenkov Log Triple: [Ganina Yama, nearbySite, Porosenkov Log]
Generated description
Porosenkov Log is a forested area near Yekaterinburg, Russia, known as one of the sites associated with the execution and secret burial of the last Russian imperial family, the Romanovs.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Porosenkov Log Target entity description: Porosenkov Log is a forested area near Yekaterinburg, Russia, known as one of the sites associated with the execution and secret burial of the last Russian imperial family, the Romanovs.
-
A.
Oreshek
Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
-
B.
Kologriv
Kologriv is a small historic town in Kostroma Oblast, Russia, known for its traditional wooden architecture and location within a forested, sparsely populated region.
-
C.
Khovrino
Khovrino is a Moscow Metro station serving as the northern terminus of the Zamoskvoretskaya Line.
-
D.
Sergiyev
Sergiyev is the former name of the Russian town now known as Sergiyev Posad, a historic center of Orthodox Christianity northeast of Moscow.
-
E.
Vyazemsky
Vyazemsky is a small town in Russia’s Far Eastern Federal District, serving as an administrative center within Khabarovsk Krai.
- 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_69bd4465e03081909bfcfd7113062590 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7abd3ed48190bfd8d2f2ca399741 |
completed | March 20, 2026, 4:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beeff852bc81908467a343c5ded404 |
completed | March 21, 2026, 7:22 p.m. |
| NEDg | Description generation | batch_69bef0761c208190bac06ff1f92c8224 |
completed | March 21, 2026, 7:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bef14ca27c81909a5a44155c9ddaf9 |
completed | March 21, 2026, 7:28 p.m. |
Created at: March 20, 2026, 1:48 p.m.