Triple

T11885393
Position Surface form Disambiguated ID Type / Status
Subject Ijebu people E282766 entity
Predicate traditionalReligionDeity P5606 FINISHED
Object Sango
Sango is a powerful Yoruba thunder and lightning deity widely venerated across southwestern Nigeria and in the African diaspora.
E952037 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: Sango | Statement: [Ijebu people, traditionalReligionDeity, Sango]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sango
Context triple: [Ijebu people, traditionalReligionDeity, Sango]
  • A. Sango
    Sango is a Central African lingua franca and national language of the Central African Republic, originating as a Ngbandi-based trade language.
  • B. Tanno
    Tanno is a district or locality within the city of Kitami in Hokkaido, Japan.
  • C. Ogunai
    Ogunai is a small riverside settlement located along the Fly River in Papua New Guinea.
  • D. Masego
    Masego is an American musician, singer, and producer known for his genre-blending "TrapHouseJazz" style that fuses jazz, R&B, and hip-hop.
  • E. Shingu
    Shingu is a coastal city in Japan known for its historic Kumano Hongu Taisha shrine and its role as a gateway to the sacred Kumano Kodo pilgrimage routes.
  • 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: Sango
Triple: [Ijebu people, traditionalReligionDeity, Sango]
Generated description
Sango is a powerful Yoruba thunder and lightning deity widely venerated across southwestern Nigeria and in the African diaspora.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sango
Target entity description: Sango is a powerful Yoruba thunder and lightning deity widely venerated across southwestern Nigeria and in the African diaspora.
  • A. Sango
    Sango is a Central African lingua franca and national language of the Central African Republic, originating as a Ngbandi-based trade language.
  • B. Tanno
    Tanno is a district or locality within the city of Kitami in Hokkaido, Japan.
  • C. Ogunai
    Ogunai is a small riverside settlement located along the Fly River in Papua New Guinea.
  • D. Masego
    Masego is an American musician, singer, and producer known for his genre-blending "TrapHouseJazz" style that fuses jazz, R&B, and hip-hop.
  • E. Shingu
    Shingu is a coastal city in Japan known for its historic Kumano Hongu Taisha shrine and its role as a gateway to the sacred Kumano Kodo pilgrimage routes.
  • 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_69d6ab2a90b08190a4e818821cc93e6d completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8d3a13370819086386fecb99e4f0b completed April 10, 2026, 10:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69f281f488a8819082f40dfdd12f29a2 completed April 29, 2026, 10:11 p.m.
NEDg Description generation batch_69f2d6da770481908cd8787ba6b5763b completed April 30, 2026, 4:13 a.m.
NED2 Entity disambiguation (via description) batch_69f2dc57c3888190920b4275ed0b5bff completed April 30, 2026, 4:36 a.m.
Created at: April 8, 2026, 9:44 p.m.