Triple

T18902646
Position Surface form Disambiguated ID Type / Status
Subject Throne of Jade E462372 entity
Predicate hasCharacter P2308 FINISHED
Object Berkley 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: Berkley | Statement: [Throne of Jade, hasCharacter, Berkley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berkley
Context triple: [Throne of Jade, hasCharacter, Berkley]
  • A. Berkley
    Berkley is a small rural town in Bristol County, Massachusetts, known for its quiet residential character and proximity to the Taunton River.
  • B. Berkley chosen
    Berkley is a surname most notably associated with American actress Elizabeth Berkley, known for her roles in "Saved by the Bell" and "Showgirls."
  • C. Berkley, Michigan
    Berkley, Michigan is a small suburban city in Oakland County known for its tree-lined neighborhoods, family-friendly community, and proximity to Detroit.
  • D. Berkley, Massachusetts
    Berkley, Massachusetts is a small rural town in southeastern Massachusetts known for its quiet residential character and location along the Taunton River.
  • E. Berkelland
    Berkelland is a municipality in the eastern Netherlands, located in the Achterhoek region of the province of Gelderland.
  • 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_69d8dcfd05bc819088903cca13cc2846 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c52a4b4c8190b5821996e3c1741d completed April 20, 2026, 6:18 a.m.
Created at: April 10, 2026, 11:58 a.m.