Triple

T7415407
Position Surface form Disambiguated ID Type / Status
Subject Royal Palaces of Abomey E171114 entity
Predicate builtForRuler P76816 FINISHED
Object Behanzin
Behanzin was the last independent king of the Kingdom of Dahomey, known for his resistance against French colonial conquest in the late 19th century.
 E663929 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: Behanzin | Statement: [Royal Palaces of Abomey, builtForRuler, Behanzin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Behanzin
Context triple: [Royal Palaces of Abomey, builtForRuler, Behanzin]
  • A. Herse
    Herse is a small, irregular outer moon of Jupiter belonging to the planet’s distant, retrograde satellite group.
  • B. Galanta
    Galanta is a town in southern Slovakia known as a regional center with historical ties to the Esterházy noble family.
  • C. Orgelet
    Orgelet is a small commune in eastern France’s Jura department, known for its proximity to the scenic Vouglans Reservoir and the surrounding lake and forest landscapes.
  • D. Zezuru
    Zezuru is a major dialect of the Shona language spoken primarily in central and northern Zimbabwe.
  • E. Zegelsem
    Zegelsem is a village in the Flemish Ardennes region of East Flanders, Belgium, known for its rural character and cobblestone cycling roads.
  • 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: Behanzin
Triple: [Royal Palaces of Abomey, builtForRuler, Behanzin]
Generated description
Behanzin was the last independent king of the Kingdom of Dahomey, known for his resistance against French colonial conquest in the late 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Behanzin
Target entity description: Behanzin was the last independent king of the Kingdom of Dahomey, known for his resistance against French colonial conquest in the late 19th century.
  • A. Herse
    Herse is a small, irregular outer moon of Jupiter belonging to the planet’s distant, retrograde satellite group.
  • B. Galanta
    Galanta is a town in southern Slovakia known as a regional center with historical ties to the Esterházy noble family.
  • C. Orgelet
    Orgelet is a small commune in eastern France’s Jura department, known for its proximity to the scenic Vouglans Reservoir and the surrounding lake and forest landscapes.
  • D. Zezuru
    Zezuru is a major dialect of the Shona language spoken primarily in central and northern Zimbabwe.
  • E. Zegelsem
    Zegelsem is a village in the Flemish Ardennes region of East Flanders, Belgium, known for its rural character and cobblestone cycling roads.
  • 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_69c68a618bdc81908d8018edadecd1a4 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f4ec85488190a1f7fb913e0fbe35 completed March 27, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c81ee704a8819088f72135272404cb completed March 28, 2026, 6:33 p.m.
NEDg Description generation batch_69c81fb91eb88190b6436ace69d44211 completed March 28, 2026, 6:36 p.m.
NED2 Entity disambiguation (via description) batch_69c822f547388190be0879b70542a421 completed March 28, 2026, 6:50 p.m.
Created at: March 27, 2026, 3:11 p.m.