Triple

T10971536
Position Surface form Disambiguated ID Type / Status
Subject Max Irons E259246 entity
Predicate educatedAt P5 FINISHED
Object Dragon School E249935 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: Dragon School | Statement: [Max Irons, educatedAt, Dragon School]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dragon School
Context triple: [Max Irons, educatedAt, Dragon School]
  • A. Dragon School chosen
    Dragon School is a prestigious preparatory school in Oxford, England, known for educating many notable British actors, writers, and public figures.
  • B. Minue School
    Minue School is a public elementary school serving young students in the community of Carteret, New Jersey.
  • C. Magnaura School
    Magnaura School was a prestigious educational institution in Constantinople associated with the Byzantine imperial court and higher learning.
  • D. Red Brick School
    Red Brick School is a historic one-room schoolhouse in Franklin, Massachusetts, recognized as one of the oldest continuously used school buildings in the United States.
  • E. Pikemere School
    Pikemere School is a primary school located in the town of Alsager in Cheshire, England.
  • 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_69d6aa895f4c8190887a15460ef622f4 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7719b5edc81908c1019f81e78bd2e completed April 9, 2026, 9:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d790df108190b4a3a6fece372778 completed April 18, 2026, 1 a.m.
Created at: April 8, 2026, 9:24 p.m.