Triple

T12888060
Position Surface form Disambiguated ID Type / Status
Subject André Louw E308281 entity
Predicate familyName P18 FINISHED
Object Louw E52513 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: Louw | Statement: [André Louw, familyName, Louw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louw
Context triple: [André Louw, familyName, Louw]
  • A. Louw chosen
    Louw is a surname of Afrikaans and Dutch origin borne by several notable South African figures, including writers and public personalities.
  • B. Lourens
    Lourens is a given name derived from the Latin name Laurentius, commonly used in Dutch and Afrikaans contexts.
  • C. Marais Louw
    Marais Louw is a South African rugby union player known for his performances as a flanker in domestic and international competitions.
  • D. Lewan
    Lewan is an archaeological site in Pakistan’s Bannu Basin known for evidence of ancient human settlement and cultural development.
  • E. De Wit
    De Wit is a Dutch surname commonly borne by individuals of Dutch origin and often associated with historical figures from the Netherlands.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9714581988190afc720ffd7797860 completed April 10, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a5576ae4819084914697b2e86d9f completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:39 p.m.