Triple

T22907936
Position Surface form Disambiguated ID Type / Status
Subject Andre Keyser E568502 entity
Predicate notableSite P2462 FINISHED
Object Drimolen NE NERFINISHED

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: Drimolen | Statement: [Andre Keyser, notableSite, Drimolen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Drimolen
Context triple: [Andre Keyser, notableSite, Drimolen]
  • A. Drimolen chosen
    Drimolen is an important South African paleoanthropological cave site known for yielding significant early hominin fossils within the Cradle of Humankind World Heritage area.
  • B. Kromdraai
    Kromdraai is a renowned paleoanthropological site in South Africa’s Cradle of Humankind, known for yielding important early hominin fossils.
  • C. Pulamanthole
    Pulamanthole is a town in the Malappuram district of Kerala, India, known for its local commerce and role as a regional hub for surrounding rural areas.
  • D. Brobenah
    Brobenah is a rural locality within the Leeton Shire area of New South Wales, Australia.
  • E. Mazabuka
    Mazabuka is a town in southern Zambia known for its sugar industry and agricultural production.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2458cd9e48190943ad2e34485d939 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18071b9ec81908922d5f046f7930a completed April 29, 2026, 3:52 a.m.
Created at: April 17, 2026, 3:42 p.m.