Triple

T18722275
Position Surface form Disambiguated ID Type / Status
Subject CoBrA E457805 entity
Predicate hasMember P10 FINISHED
Object Pierre Alechinsky 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: Pierre Alechinsky | Statement: [CoBrA, hasMember, Pierre Alechinsky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pierre Alechinsky
Context triple: [CoBrA, hasMember, Pierre Alechinsky]
  • A. Pierre Alechinsky chosen
    Pierre Alechinsky is a Belgian painter and printmaker known for his expressive, often calligraphic style and his association with postwar European avant-garde art.
  • B. Marcel Bezençon
    Marcel Bezençon was a Swiss journalist and media executive best known as the founder of the Eurovision Song Contest.
  • C. Pierre Benoit
    Pierre Benoit was a prominent French Dominican biblical scholar and theologian known for his influential work on the New Testament and his leadership at Jerusalem’s École Biblique.
  • D. Marcel Sembat
    Marcel Sembat is a Paris Métro station located in the western suburb of Boulogne-Billancourt, serving as part of the city's Line 9 network.
  • E. Henri Ponsot
    Henri Ponsot was a French diplomat and colonial administrator best known for his high-ranking roles in France’s North African protectorates during the early 20th century.
  • 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56abc1c708190917f6bfea0548c42 completed April 19, 2026, 11:52 p.m.
Created at: April 10, 2026, 11:50 a.m.