Triple

T10391646
Position Surface form Disambiguated ID Type / Status
Subject Coming Through Slaughter E244905 entity
Predicate publisher P29 FINISHED
Object Anansi E625855 NE FINISHED

How this triple was built (2 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: Anansi | Statement: [Coming Through Slaughter, publisher, Anansi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anansi
Context triple: [Coming Through Slaughter, publisher, Anansi]
  • A. Anansi chosen
    Anansi is a trickster spider-god from West African and Caribbean folklore, known for his cleverness, storytelling, and role in outwitting more powerful beings.
  • B. Onyankopon
    Onyankopon is the supreme sky god and creator figure in the traditional religion of the Akan people of West Africa.
  • C. Malongo
    Malongo is a major offshore oil field and production hub located off the coast of Cabinda in Angola.
  • D. Okiek
    Okiek is a Southern Nilotic language spoken by the Okiek (Ogiek) people of Kenya and Tanzania, known for their traditional forest-dwelling hunter-gatherer culture.
  • E. Kwaku
    Kwaku is a Ghanaian given name traditionally borne by males born on a Wednesday in Akan culture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9b5b43081908641a5abfb08dc2b completed April 7, 2026, 11:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69d795b9974c819087340adc3622279e completed April 9, 2026, 12:04 p.m.
Created at: April 6, 2026, 12:06 p.m.