Triple

T12630450
Position Surface form Disambiguated ID Type / Status
Subject Greeks of Azov E301625 entity
Predicate mainCity P3207 FINISHED
Object Sartana
Sartana is a historically Greek-populated settlement near Mariupol in eastern Ukraine, known as a cultural center of the local Greek (Azov Greek) community.
 E994576 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: Sartana | Statement: [Greeks of Azov, mainCity, Sartana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sartana
Context triple: [Greeks of Azov, mainCity, Sartana]
  • A. Saho
    Saho is a Cushitic language spoken primarily by the Saho people in Eritrea and neighboring regions of the Horn of Africa.
  • B. Pantami
    Pantami is a town and district in Gombe State, northeastern Nigeria, known for its role as a local administrative and commercial center.
  • C. Rammu
    Rammu is a small Estonian island in the Gulf of Finland, known for its natural landscapes and sparse habitation.
  • D. Palooka
    Palooka is a 1934 American comedy film based on the popular comic strip about a naive but talented boxer, starring Jimmy Durante and Lupe Vélez.
  • E. Bindo
    Bindo is an Italian given name, notably borne by Bindo Maserati, a member of the family behind the Maserati automobile marque.
  • 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: Sartana
Triple: [Greeks of Azov, mainCity, Sartana]
Generated description
Sartana is a historically Greek-populated settlement near Mariupol in eastern Ukraine, known as a cultural center of the local Greek (Azov Greek) community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sartana
Target entity description: Sartana is a historically Greek-populated settlement near Mariupol in eastern Ukraine, known as a cultural center of the local Greek (Azov Greek) community.
  • A. Saho
    Saho is a Cushitic language spoken primarily by the Saho people in Eritrea and neighboring regions of the Horn of Africa.
  • B. Pantami
    Pantami is a town and district in Gombe State, northeastern Nigeria, known for its role as a local administrative and commercial center.
  • C. Rammu
    Rammu is a small Estonian island in the Gulf of Finland, known for its natural landscapes and sparse habitation.
  • D. Palooka
    Palooka is a 1934 American comedy film based on the popular comic strip about a naive but talented boxer, starring Jimmy Durante and Lupe Vélez.
  • E. Bindo
    Bindo is an Italian given name, notably borne by Bindo Maserati, a member of the family behind the Maserati automobile marque.
  • 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_69d7bdeaf49c8190b13800111fa77ea3 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9610ce9e48190a496824002c0d2be completed April 10, 2026, 8:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6686f9ba48190bd82b2bb037d7d7a completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f6697d8ac88190b4ead9ce47f3a705 completed May 2, 2026, 9:15 p.m.
NED2 Entity disambiguation (via description) batch_69f66a2da60881909b0a689821456bb4 completed May 2, 2026, 9:18 p.m.
Created at: April 9, 2026, 5:15 p.m.