Triple

T14209527
Position Surface form Disambiguated ID Type / Status
Subject King Béhanzin E352190 entity
Predicate birthName P65 FINISHED
Object Kondo
Kondo was the birth name of King Béhanzin, the last independent ruler of the Kingdom of Dahomey in West Africa.
 E1085818 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: Kondo | Statement: [King Béhanzin, birthName, Kondo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kondo
Context triple: [King Béhanzin, birthName, Kondo]
  • A. Kondo
    Kondo is the main hall of Yakushi-ji Temple in Nara, Japan, renowned for enshrining important Buddhist images and serving as the temple’s central worship space.
  • B. Takaichi
    Takaichi is a Japanese surname most prominently associated with conservative politician Sanae Takaichi.
  • C. Norikura
    Norikura is a ski resort area in Japan’s Hakuba Valley, known for its scenic alpine terrain and winter sports opportunities.
  • D. Shuji
    Shuji is a Japanese given name most notably borne by Nobel Prize–winning physicist Shuji Nakamura.
  • E. Warekena
    The Warekena are an Indigenous people of the Amazon region, primarily living along rivers in Brazil and Venezuela, known for their distinct Arawakan language and traditional riverine lifestyle.
  • 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: Kondo
Triple: [King Béhanzin, birthName, Kondo]
Generated description
Kondo was the birth name of King Béhanzin, the last independent ruler of the Kingdom of Dahomey in West Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kondo
Target entity description: Kondo was the birth name of King Béhanzin, the last independent ruler of the Kingdom of Dahomey in West Africa.
  • A. Kondo
    Kondo is the main hall of Yakushi-ji Temple in Nara, Japan, renowned for enshrining important Buddhist images and serving as the temple’s central worship space.
  • B. Takaichi
    Takaichi is a Japanese surname most prominently associated with conservative politician Sanae Takaichi.
  • C. Norikura
    Norikura is a ski resort area in Japan’s Hakuba Valley, known for its scenic alpine terrain and winter sports opportunities.
  • D. Shuji
    Shuji is a Japanese given name most notably borne by Nobel Prize–winning physicist Shuji Nakamura.
  • E. Warekena
    The Warekena are an Indigenous people of the Amazon region, primarily living along rivers in Brazil and Venezuela, known for their distinct Arawakan language and traditional riverine lifestyle.
  • 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_69d8278a06e481908b5d6af0a8afe737 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61fa8d24819092a8ec5d34c1c799 completed April 14, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd19557f908190abb3dc116676f215 completed May 7, 2026, 10:59 p.m.
NEDg Description generation batch_69fd1b198c6c81909b71a51a39711754 completed May 7, 2026, 11:07 p.m.
NED2 Entity disambiguation (via description) batch_69fd1bb585448190bc3393304980b808 completed May 7, 2026, 11:09 p.m.
Created at: April 10, 2026, 1:05 a.m.