Triple

T19918216
Position Surface form Disambiguated ID Type / Status
Subject The Shining Girls E478719 entity
Predicate publisher P29 FINISHED
Object Umuzi
Umuzi is a South African publishing imprint of Penguin Random House known for releasing contemporary and literary fiction by local and international authors.
E1402100 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: Umuzi | Statement: [The Shining Girls, publisher, Umuzi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Umuzi
Context triple: [The Shining Girls, publisher, Umuzi]
  • A. Umzinto
    Umzinto is a town in the KwaZulu-Natal province of South Africa, historically known for its sugar industry and diverse local community.
  • B. Muntu
    Muntu is a seminal play by Ghanaian dramatist Joe de Graft that explores African identity, history, and postcolonial experience through allegory and poetic drama.
  • C. Utsetela
    Utsetela is a little-known genus of flowering plants in the mulberry and fig family, Moraceae.
  • D. Usuthu
    Usuthu is the popular nickname of AmaZulu F.C., a professional football club based in Durban, South Africa.
  • E. Puthandu
    Puthandu is the Tamil New Year festival, celebrated primarily in the Indian state of Tamil Nadu and by Tamil communities worldwide with rituals, feasting, and cultural traditions.
  • 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: Umuzi
Triple: [The Shining Girls, publisher, Umuzi]
Generated description
Umuzi is a South African publishing imprint of Penguin Random House known for releasing contemporary and literary fiction by local and international authors.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Umuzi
Target entity description: Umuzi is a South African publishing imprint of Penguin Random House known for releasing contemporary and literary fiction by local and international authors.
  • A. Umzinto
    Umzinto is a town in the KwaZulu-Natal province of South Africa, historically known for its sugar industry and diverse local community.
  • B. Muntu
    Muntu is a seminal play by Ghanaian dramatist Joe de Graft that explores African identity, history, and postcolonial experience through allegory and poetic drama.
  • C. Utsetela
    Utsetela is a little-known genus of flowering plants in the mulberry and fig family, Moraceae.
  • D. Usuthu
    Usuthu is the popular nickname of AmaZulu F.C., a professional football club based in Durban, South Africa.
  • E. Puthandu
    Puthandu is the Tamil New Year festival, celebrated primarily in the Indian state of Tamil Nadu and by Tamil communities worldwide with rituals, feasting, and cultural traditions.
  • 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659c3d990819089386d9f30323e8c completed April 20, 2026, 4:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ea52592481909419476f335b6046 completed May 16, 2026, 3:53 a.m.
NEDg Description generation batch_6a07f2c7dec48190a698509098479a56 completed May 16, 2026, 4:30 a.m.
NED2 Entity disambiguation (via description) batch_6a07f376f5388190989a0460528945df completed May 16, 2026, 4:32 a.m.
Created at: April 10, 2026, 1:53 p.m.