Triple

T11469060
Position Surface form Disambiguated ID Type / Status
Subject Khoi-San E271853 entity
Predicate composedOf P402 FINISHED
Object San E353771 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: San | Statement: [Khoi-San, composedOf, San]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: San
Context triple: [Khoi-San, composedOf, San]
  • A. San chosen
    The San are an indigenous hunter-gatherer people of Southern Africa, known for their ancient rock art, click-based languages, and deep ecological knowledge of the Kalahari region.
  • B. San Jo
    San Jo is an informal nickname commonly used to refer to the city of San Jose, California.
  • C. Vale do São Francisco
    Vale do São Francisco is a major river valley region in northeastern Brazil known for its irrigated agriculture, especially fruit and wine production, along the São Francisco River.
  • D. Rivera, California
    Rivera, California was a former unincorporated community in Los Angeles County that later became part of the city of Pico Rivera.
  • E. São Francisco
    São Francisco is a locality or neighborhood within the municipality of Alcochete in Portugal, known for its residential character and proximity to the Tagus estuary.
  • 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_69d6aae0c8d881908a5a360c0be3242e completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d822f74144819094479690c8151073 completed April 9, 2026, 10:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5e94ea4748190b375e644b2f1a46c completed April 20, 2026, 8:52 a.m.
Created at: April 8, 2026, 9:35 p.m.