Triple

T1713165
Position Surface form Disambiguated ID Type / Status
Subject Sandy E37229 entity
Predicate relatedName P3889 FINISHED
Object Sander E136997 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: Sander | Statement: [Sandy, relatedName, Sander]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sander
Context triple: [Sandy, relatedName, Sander]
  • A. Zander
    Zander is a given name, often used as a variant or short form of Alexander, that can function as either a first name or surname.
  • B. Schalk
    Schalk is a masculine given name of Afrikaans and Dutch origin, commonly used in South Africa.
  • C. Sander Loones chosen
    Sander Loones is a Belgian politician and member of the New Flemish Alliance (N-VA) who has served in both national and European political roles.
  • D. Janson
    Janson is a surname and given name of European origin, often considered a variant of Jackson.
  • E. Sven
    Sven is the lovable reindeer companion in Disney's animated film "Frozen," known for his close bond with Kristoff and his expressive, dog-like personality.
  • 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_69a8861912dc8190931af43b4b9158a7 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa63174b3c8190bd2406c78407be28 completed March 6, 2026, 5:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada0d1882c81908e02e36ab28e7fdc completed March 8, 2026, 4:16 p.m.
Created at: March 4, 2026, 7:30 p.m.