Triple

T18852848
Position Surface form Disambiguated ID Type / Status
Subject Mary Hanson E461088 entity
Predicate relative P37 FINISHED
Object Peter Larsen 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: Peter Larsen | Statement: [Mary Hanson, relative, Peter Larsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Larsen
Context triple: [Mary Hanson, relative, Peter Larsen]
  • A. Peter Larsen chosen
    Peter Larsen is an individual known primarily as the husband of Mary Hanson.
  • B. Jonathan Larsen
    Jonathan Larsen is a New Zealand local government politician who serves as the deputy mayor of the Kaipara District.
  • C. Henrik Larsen
    Henrik Larsen is a former Danish footballer best known for his crucial goals in Denmark’s surprise victory at UEFA Euro 1992, where he finished as one of the tournament’s top scorers.
  • D. Alhed Larsen
    Alhed Larsen was a Danish painter associated with the Funen Painters, known for her intimate interiors, floral still lifes, and contributions to early 20th-century Danish art.
  • E. Johannes Larsen
    Johannes Larsen was a Danish painter renowned for his nature and bird motifs and as a central figure of the Funen Painters art movement.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c05a8a708190b9b2b8f95b2f1d23 completed April 20, 2026, 5:57 a.m.
Created at: April 10, 2026, 11:56 a.m.