Triple

T558235
Position Surface form Disambiguated ID Type / Status
Subject Expressionism E11990 entity
Predicate notableWork P4 FINISHED
Object The Large Blue Horses E69929 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: The Large Blue Horses | Statement: [Expressionism, notableWork, The Large Blue Horses]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Large Blue Horses
Context triple: [Expressionism, notableWork, The Large Blue Horses]
  • A. White Horses
    White Horses is a small coastal settlement in the parish of St. Thomas in eastern Jamaica.
  • B. The Golden Stallion
    The Golden Stallion is a 1949 Western film starring singing cowboy Roy Rogers and his famous horse Trigger, blending action, music, and adventure.
  • C. Blue Horse I chosen
    Blue Horse I is a famous 1911 Expressionist painting by Franz Marc, depicting a stylized blue horse that has become an iconic symbol of German Expressionism.
  • D. Come to the Stable
    Come to the Stable is a 1949 American comedy-drama film about two French nuns trying to build a children's hospital in New England.
  • E. De Heraut
    De Heraut was a Dutch Reformed newspaper associated with theologian and statesman Abraham Kuyper and his neo-Calvinist movement.
  • 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_69a4932941d08190815efd422f0b4ca7 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a499df43f08190b514a38d36fc271d completed March 1, 2026, 7:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4e9bb3b28819099ed0027d948483a completed March 2, 2026, 1:36 a.m.
Created at: March 1, 2026, 7:32 p.m.