Triple

T8646869
Position Surface form Disambiguated ID Type / Status
Subject Tsakonia E204997 entity
Predicate containsSettlement P847 FINISHED
Object Vaskina
Vaskina is a small settlement located in the traditional Tsakonian region of the eastern Peloponnese in Greece.
 E747777 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: Vaskina | Statement: [Tsakonia, containsSettlement, Vaskina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vaskina
Context triple: [Tsakonia, containsSettlement, Vaskina]
  • A. Oreshek
    Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
  • B. Sosva
    Sosva is a rural locality in Sverdlovsk Oblast, Russia, historically known as the site of a Soviet-era labor camp where Finnish communist leader Kullervo Manner died.
  • C. Kvasy
    Kvasy is a village in western Ukraine’s Zakarpattia region, known as a starting point for hikes in the Carpathian Mountains and for its mineral springs.
  • D. Vishkanya
    Vishkanya is a 1991 Indian Hindi-language horror film known for its supernatural revenge plot and early appearance of actress Riya Sen.
  • E. Vassa
    Vassa is the traditional Buddhist rainy-season retreat during which monks remain in one place for intensive meditation and study.
  • 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: Vaskina
Triple: [Tsakonia, containsSettlement, Vaskina]
Generated description
Vaskina is a small settlement located in the traditional Tsakonian region of the eastern Peloponnese in Greece.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vaskina
Target entity description: Vaskina is a small settlement located in the traditional Tsakonian region of the eastern Peloponnese in Greece.
  • A. Oreshek
    Oreshek is the historic Russian fortress on Lake Ladoga that later gave rise to the town of Shlisselburg.
  • B. Sosva
    Sosva is a rural locality in Sverdlovsk Oblast, Russia, historically known as the site of a Soviet-era labor camp where Finnish communist leader Kullervo Manner died.
  • C. Kvasy
    Kvasy is a village in western Ukraine’s Zakarpattia region, known as a starting point for hikes in the Carpathian Mountains and for its mineral springs.
  • D. Vishkanya
    Vishkanya is a 1991 Indian Hindi-language horror film known for its supernatural revenge plot and early appearance of actress Riya Sen.
  • E. Vassa
    Vassa is the traditional Buddhist rainy-season retreat during which monks remain in one place for intensive meditation and study.
  • 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_69ca834e56848190abb0eeaec9dedd32 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc480eb7f88190a38d2150976cd47f completed March 31, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebc4883cc8190a6fb72005ca99512 completed April 2, 2026, 6:58 p.m.
NEDg Description generation batch_69cebd2cb2e481909a2862e79482c37a completed April 2, 2026, 7:02 p.m.
NED2 Entity disambiguation (via description) batch_69cebdd77b6c81908c35ee96dfe053d8 completed April 2, 2026, 7:04 p.m.
Created at: March 30, 2026, 6:28 p.m.