Triple

T8953723
Position Surface form Disambiguated ID Type / Status
Subject Kaneš E213419 entity
Predicate excavatedBy P7650 FINISHED
Object Kökten
Kökten is an archaeologist known for conducting excavations at the ancient Anatolian site of Kaneš (Kültepe) in modern-day Turkey.
E767959 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: Kökten | Statement: [Kaneš, excavatedBy, Kökten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kökten
Context triple: [Kaneš, excavatedBy, Kökten]
  • A. Vöcklabruck
    Vöcklabruck is a small historic town in Upper Austria known as a regional center near the Attersee lake and the foothills of the Alps.
  • B. Klosterneuburg
    Klosterneuburg is an Austrian town near Vienna, known for its historic Augustinian monastery and wine-growing tradition along the Danube River.
  • C. Kozelets
    Kozelets is an urban-type settlement in northern Ukraine, historically known as a local administrative and trading center.
  • D. Leoben
    Leoben is a historic industrial and university city in the Austrian state of Styria, known especially for its steel industry and mining university.
  • E. Karlowitz
    Karlowitz is a historic town in present-day Sremski Karlovci, Serbia, known as the site where the 1699 Treaty of Karlowitz was concluded between the Habsburg Monarchy and the Ottoman Empire.
  • 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: Kökten
Triple: [Kaneš, excavatedBy, Kökten]
Generated description
Kökten is an archaeologist known for conducting excavations at the ancient Anatolian site of Kaneš (Kültepe) in modern-day Turkey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kökten
Target entity description: Kökten is an archaeologist known for conducting excavations at the ancient Anatolian site of Kaneš (Kültepe) in modern-day Turkey.
  • A. Vöcklabruck
    Vöcklabruck is a small historic town in Upper Austria known as a regional center near the Attersee lake and the foothills of the Alps.
  • B. Klosterneuburg
    Klosterneuburg is an Austrian town near Vienna, known for its historic Augustinian monastery and wine-growing tradition along the Danube River.
  • C. Kozelets
    Kozelets is an urban-type settlement in northern Ukraine, historically known as a local administrative and trading center.
  • D. Leoben
    Leoben is a historic industrial and university city in the Austrian state of Styria, known especially for its steel industry and mining university.
  • E. Karlowitz
    Karlowitz is a historic town in present-day Sremski Karlovci, Serbia, known as the site where the 1699 Treaty of Karlowitz was concluded between the Habsburg Monarchy and the Ottoman Empire.
  • 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_69ca8399ad2081909f8fa41d4314c215 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc670f88d0819085d7308a5cf6c764 completed April 1, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc210302c8190b1c062fcbcfeb0f6 completed April 3, 2026, 1:35 p.m.
NEDg Description generation batch_69cfc34eba0881908155770166639481 completed April 3, 2026, 1:40 p.m.
NED2 Entity disambiguation (via description) batch_69cfc41fca3081908d8c2515c98283de completed April 3, 2026, 1:43 p.m.
Created at: March 30, 2026, 7 p.m.