Triple

T11818043
Position Surface form Disambiguated ID Type / Status
Subject Elegguá E281052 entity
Predicate associatedWithOrisha P69792 FINISHED
Object Ochosi
Ochosi is an orisha in the Yoruba and Afro-Caribbean religious traditions, revered as a divine hunter, tracker, and guardian of justice.
E948153 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: Ochosi | Statement: [Elegguá, associatedWithOrisha, Ochosi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ochosi
Context triple: [Elegguá, associatedWithOrisha, Ochosi]
  • A. Othomi
    Othomi is an alternative name for the Otomi people and their indigenous language of central Mexico.
  • B. Okondja
    Okondja is a town in southeastern Gabon known as a local administrative and economic center within the Haut-Ogooué region.
  • C. Oshikwambi
    Oshikwambi is a regional dialect of the Oshiwambo language spoken by the Kwambi people in northern Namibia.
  • D. Ofolanga
    Ofolanga is a small island in the Haʻapai group of Tonga, known for its remote, unspoiled beaches and traditional Polynesian character.
  • E. Ndowe
    Ndowe is a Bantu language spoken by the Ndowe people along the coastal region of Equatorial Guinea.
  • 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: Ochosi
Triple: [Elegguá, associatedWithOrisha, Ochosi]
Generated description
Ochosi is an orisha in the Yoruba and Afro-Caribbean religious traditions, revered as a divine hunter, tracker, and guardian of justice.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ochosi
Target entity description: Ochosi is an orisha in the Yoruba and Afro-Caribbean religious traditions, revered as a divine hunter, tracker, and guardian of justice.
  • A. Othomi
    Othomi is an alternative name for the Otomi people and their indigenous language of central Mexico.
  • B. Okondja
    Okondja is a town in southeastern Gabon known as a local administrative and economic center within the Haut-Ogooué region.
  • C. Oshikwambi
    Oshikwambi is a regional dialect of the Oshiwambo language spoken by the Kwambi people in northern Namibia.
  • D. Ofolanga
    Ofolanga is a small island in the Haʻapai group of Tonga, known for its remote, unspoiled beaches and traditional Polynesian character.
  • E. Ndowe
    Ndowe is a Bantu language spoken by the Ndowe people along the coastal region of Equatorial Guinea.
  • 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_69d6ab26aae88190b2489efcb2a24234 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8be15fb2481908f514781ce2c617f completed April 10, 2026, 9:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f131cbf9708190ba8394fb3508b975 completed April 28, 2026, 10:16 p.m.
NEDg Description generation batch_69f14e8a1b788190a1704d6e102342e3 completed April 29, 2026, 12:19 a.m.
NED2 Entity disambiguation (via description) batch_69f15715a1588190ba0ec21647adc57c completed April 29, 2026, 12:55 a.m.
Created at: April 8, 2026, 9:42 p.m.