Triple

T13019042
Position Surface form Disambiguated ID Type / Status
Subject Gardians E322627 entity
Predicate useAnimal P16495 FINISHED
Object Camargue horse E61990 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: Camargue horse | Statement: [Gardians, useAnimal, Camargue horse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Camargue horse
Context triple: [Gardians, useAnimal, Camargue horse]
  • A. Camargue horse chosen
    The Camargue horse is an ancient, small, and hardy gray horse breed native to the marshes of southern France, renowned for its sure-footedness and use in traditional cattle herding.
  • B. Konik horses
    Konik horses are a hardy, semi-wild Polish horse breed known for their primitive features and use in conservation grazing to maintain natural landscapes.
  • C. Dala horse
    The Dala horse is a traditional carved and painted wooden horse from Sweden, widely recognized as a national folk art icon and symbol of Swedish heritage.
  • D. Akhal-Teke horse
    The Akhal-Teke horse is an ancient Turkmen breed renowned for its metallic sheen, exceptional endurance, and refined, athletic build.
  • E. Franches-Montagnes horse
    The Franches-Montagnes horse is a versatile Swiss light draft and riding breed known for its strength, sure-footedness, and calm temperament.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d9804b743c8190810dc5c14bc6d912 completed April 10, 2026, 10:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d5f861188190892b4d693395cc5e completed May 3, 2026, 4:58 a.m.
Created at: April 9, 2026, 8:51 p.m.