Triple

T12669501
Position Surface form Disambiguated ID Type / Status
Subject John Kani E302636 entity
Predicate spouse P13 FINISHED
Object Mandi Kani
Mandi Kani is the wife of renowned South African actor, director, and playwright John Kani.
 E995420 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: Mandi Kani | Statement: [John Kani, spouse, Mandi Kani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mandi Kani
Context triple: [John Kani, spouse, Mandi Kani]
  • A. Manjai Kunda
    Manjai Kunda is a residential neighborhood within the urban area of Serekunda in The Gambia.
  • B. Banshiwala
    Banshiwala is a Bengali novel by acclaimed writer Shirshendu Mukhopadhyay, known for its evocative storytelling and exploration of human relationships.
  • C. Shekhani
    Shekhani is a dialect of the Kati language spoken by communities in parts of Afghanistan and Pakistan.
  • D. Chhalia
    Chhalia is a 1960 Hindi-language Bollywood drama film directed by Manmohan Desai and starring Raj Kapoor, known for its themes of post-Partition trauma and reconciliation.
  • E. Marda Kunama
    Marda Kunama is a regional dialect of the Kunama language spoken by the Kunama people of the Horn of Africa.
  • 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: Mandi Kani
Triple: [John Kani, spouse, Mandi Kani]
Generated description
Mandi Kani is the wife of renowned South African actor, director, and playwright John Kani.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mandi Kani
Target entity description: Mandi Kani is the wife of renowned South African actor, director, and playwright John Kani.
  • A. Manjai Kunda
    Manjai Kunda is a residential neighborhood within the urban area of Serekunda in The Gambia.
  • B. Banshiwala
    Banshiwala is a Bengali novel by acclaimed writer Shirshendu Mukhopadhyay, known for its evocative storytelling and exploration of human relationships.
  • C. Shekhani
    Shekhani is a dialect of the Kati language spoken by communities in parts of Afghanistan and Pakistan.
  • D. Chhalia
    Chhalia is a 1960 Hindi-language Bollywood drama film directed by Manmohan Desai and starring Raj Kapoor, known for its themes of post-Partition trauma and reconciliation.
  • E. Marda Kunama
    Marda Kunama is a regional dialect of the Kunama language spoken by the Kunama people of the Horn of Africa.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96183a6048190b2ef219eb9d20aa4 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6688e101481909bc3b9e13ed84632 completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f6697e3a688190abd025df1112feba completed May 2, 2026, 9:15 p.m.
NED2 Entity disambiguation (via description) batch_69f66a9230608190bfe99290ca1679fa completed May 2, 2026, 9:20 p.m.
Created at: April 9, 2026, 5:20 p.m.