Triple

T16239166
Position Surface form Disambiguated ID Type / Status
Subject Marianne Kent E394194 entity
Predicate name P16 FINISHED
Object Marianne Kent E394194 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: Marianne Kent | Statement: [Marianne Kent, name, Marianne Kent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marianne Kent
Context triple: [Marianne Kent, name, Marianne Kent]
  • A. Marianne Kent chosen
    Marianne Kent was the wife of English poet, critic, and essayist Leigh Hunt, a central figure in the Romantic literary circle.
  • B. Jean Harvey
    Jean Harvey is an actress known for her role in the British thriller film "The Man Who Finally Died."
  • C. Gillian Ayres
    Gillian Ayres was a British abstract painter renowned for her vibrant, richly textured canvases and significant contribution to postwar modern art in the UK.
  • D. Alison Surtees
    Alison Surtees is a notable individual recognized for her association with the Surtees family name.
  • E. Muriel Bagge
    Muriel Bagge is the kind, elderly Scottish woman who lovingly cares for Courage the Cowardly Dog in the animated horror-comedy series.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2455d5270819090171d4207223a28 completed April 17, 2026, 2:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000edaf76c8190acc01f58845e570a completed May 10, 2026, 4:51 a.m.
Created at: April 10, 2026, 5:04 a.m.