Triple

T15099814
Position Surface form Disambiguated ID Type / Status
Subject Sack of Tursko E360633 entity
Predicate location P40 FINISHED
Object Tursko
Tursko is a historical settlement known primarily as the site of the medieval Sack of Tursko.
E1136887 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: Tursko | Statement: [Sack of Tursko, location, Tursko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tursko
Context triple: [Sack of Tursko, location, Tursko]
  • A. Croatia
    Croatia is a southeastern European country on the Adriatic Sea, known for its historic coastal cities, thousands of islands, and status as a member of both the European Union and NATO.
  • B. Havran
    Havran is a town and district in western Turkey known for its agricultural production and location within Balıkesir Province.
  • C. Slovenia
    Slovenia is a Central European country known for its mountains, lakes, and historic cities, and is a member of both the European Union and the Eurozone.
  • D. Tunie
    Tunie is the surname of American actress and director Tamara Tunie, best known for her long-running role on "Law & Order: Special Victims Unit."
  • E. Rumen
    Rumen is a masculine given name commonly used in Bulgaria and other Slavic countries.
  • 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: Tursko
Triple: [Sack of Tursko, location, Tursko]
Generated description
Tursko is a historical settlement known primarily as the site of the medieval Sack of Tursko.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tursko
Target entity description: Tursko is a historical settlement known primarily as the site of the medieval Sack of Tursko.
  • A. Croatia
    Croatia is a southeastern European country on the Adriatic Sea, known for its historic coastal cities, thousands of islands, and status as a member of both the European Union and NATO.
  • B. Havran
    Havran is a town and district in western Turkey known for its agricultural production and location within Balıkesir Province.
  • C. Slovenia
    Slovenia is a Central European country known for its mountains, lakes, and historic cities, and is a member of both the European Union and the Eurozone.
  • D. Tunie
    Tunie is the surname of American actress and director Tamara Tunie, best known for her long-running role on "Law & Order: Special Victims Unit."
  • E. Rumen
    Rumen is a masculine given name commonly used in Bulgaria and other Slavic countries.
  • 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_69d85a035aa88190b52a139d3a1b7b6d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0054f00388190a5123d9f4a869b96 completed April 15, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae230d148190a343ac92fb089902 completed May 9, 2026, 3:46 a.m.
NEDg Description generation batch_69feb0551a508190802f4073fa5ae4b4 completed May 9, 2026, 3:56 a.m.
NED2 Entity disambiguation (via description) batch_69feb11fa1b081909243679603194b0b completed May 9, 2026, 3:59 a.m.
Created at: April 10, 2026, 3:04 a.m.