Triple

T4846714
Position Surface form Disambiguated ID Type / Status
Subject The Garden of Saint-Paul Hospital E108306 entity
Predicate related work P922 FINISHED
Object Irises E20023 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: Irises | Statement: [The Garden of Saint-Paul Hospital, related work, Irises]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irises
Context triple: [The Garden of Saint-Paul Hospital, related work, Irises]
  • A. Irises chosen
    Irises is a famous 1889 oil painting by Vincent van Gogh depicting a vibrant cluster of blooming irises, celebrated for its expressive color and dynamic composition.
  • B. Iris
    "Iris" is a hit power ballad by the Goo Goo Dolls, best known for its prominent feature on the soundtrack of the film "City of Angels."
  • C. Iris
    Iris is a powerful, genetically engineered kaiju and one of Gamera’s most formidable adversaries in the Heisei-era Gamera film series.
  • D. Iris
    Iris is a recurring character on the satirical sketch comedy series "Portlandia," known for embodying the show's quirky, offbeat humor.
  • E. Iris
    Iris is a 2001 British biographical drama film about the life and relationships of novelist and philosopher Iris Murdoch.
  • 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_69bd4409b264819085ab855f3eb5381a completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d19784c81908e256ea23889192b completed March 20, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5cd6dbcc8190b802eeb6d74fd37d completed March 21, 2026, 8:54 a.m.
Created at: March 20, 2026, 1:25 p.m.