Triple

T2918619
Position Surface form Disambiguated ID Type / Status
Subject Washington Huskies E78665 entity
Predicate mascot P52 FINISHED
Object Harry the Husky E164622 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: Harry the Husky | Statement: [Washington Huskies, mascot, Harry the Husky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry the Husky
Context triple: [Washington Huskies, mascot, Harry the Husky]
  • A. Harry the Husky chosen
    Harry the Husky is the costumed canine mascot who represents the University of Washington at athletic events and school functions.
  • B. Jonathan the Husky
    Jonathan the Husky is the costumed canine mascot representing the University of Connecticut and its athletic teams, including the renowned women’s basketball program.
  • C. Hector the Bulldog
    Hector the Bulldog is a tough, muscular bulldog character from the Looney Tunes cartoons, often portrayed as a protector of characters like Tweety.
  • D. Petey
    Petey is a diminutive nickname commonly used for people named Peter.
  • E. Jake the Dog
    Jake the Dog is a magical, shape-shifting dog and one of the two main protagonists of the animated television series Adventure Time.
  • 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_69ad8b0c2ad081909ff87050ae542bb9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad96a41b4c81909d8ace8ab270ed3c completed March 8, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b108ceccec8190807a95c29cdfb76e completed March 11, 2026, 6:16 a.m.
Created at: March 8, 2026, 2:54 p.m.