Triple

T22524512
Position Surface form Disambiguated ID Type / Status
Subject Rova of Antananarivo E556864 entity
Predicate containsBuilding P14728 FINISHED
Object Besakana
Besakana is a historically significant royal building within the Rova of Antananarivo in Madagascar, traditionally associated with Merina kingship and important state ceremonies.
 E1541100 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: Besakana | Statement: [Rova of Antananarivo, containsBuilding, Besakana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Besakana
Context triple: [Rova of Antananarivo, containsBuilding, Besakana]
  • A. Kalabahi
    Kalabahi is the main town and administrative center on Alor Island in Indonesia’s East Nusa Tenggara province.
  • B. Blawan
    Blawan is a British electronic music producer and DJ known for his dark, industrial-leaning techno and influential releases on labels like Hessle Audio and R&S Records.
  • C. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • D. Beloka
    Beloka is a small rural locality in New South Wales, Australia, situated within the Snowy Monaro region.
  • E. Bosha
    Bosha is an alternative name for the Lom people, a Romani-related ethnic group primarily found in the Caucasus region.
  • 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: Besakana
Triple: [Rova of Antananarivo, containsBuilding, Besakana]
Generated description
Besakana is a historically significant royal building within the Rova of Antananarivo in Madagascar, traditionally associated with Merina kingship and important state ceremonies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Besakana
Target entity description: Besakana is a historically significant royal building within the Rova of Antananarivo in Madagascar, traditionally associated with Merina kingship and important state ceremonies.
  • A. Kalabahi
    Kalabahi is the main town and administrative center on Alor Island in Indonesia’s East Nusa Tenggara province.
  • B. Blawan
    Blawan is a British electronic music producer and DJ known for his dark, industrial-leaning techno and influential releases on labels like Hessle Audio and R&S Records.
  • C. Kabaena
    Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
  • D. Beloka
    Beloka is a small rural locality in New South Wales, Australia, situated within the Snowy Monaro region.
  • E. Bosha
    Bosha is an alternative name for the Lom people, a Romani-related ethnic group primarily found in the Caucasus region.
  • 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_69e11e5657e881909f16ca58352c50da completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15e356b4081909d1ce911bd35fe68 completed April 29, 2026, 1:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b17f6622081909c195f490358715d completed May 18, 2026, 1:45 p.m.
NEDg Description generation batch_6a0b1a1f6af481909c403bc5a662bc1d completed May 18, 2026, 1:54 p.m.
NED2 Entity disambiguation (via description) batch_6a0b1a73d5248190b4c96165770824e0 completed May 18, 2026, 1:56 p.m.
Created at: April 16, 2026, 8:51 p.m.