Triple

T22066551
Position Surface form Disambiguated ID Type / Status
Subject Sir Percy Harris E545286 entity
Predicate givenName P17 FINISHED
Object Percy 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: Percy | Statement: [Sir Percy Harris, givenName, Percy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Percy
Context triple: [Sir Percy Harris, givenName, Percy]
  • A. Percy
    Percy is the historic English noble family that produced numerous prominent aristocrats, soldiers, and politicians, notably the Dukes of Northumberland.
  • B. Percy
    Percy is a small green saddle tank engine from the Thomas & Friends franchise, known for his youthful enthusiasm, loyalty, and occasional nervousness.
  • C. Percy
    Percy is a sadistic and cowardly prison guard from Stephen King’s novel "The Green Mile" and its film adaptation.
  • D. Percy
    Percy is a character connected to the Paradise Falls diner, likely serving as one of its notable staff or regular patrons within its narrative setting.
  • E. Percy chosen
    Percy is a masculine given name of Old French origin, famously borne by American physicist and Nobel laureate Percy W. Bridgman.
  • 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12883d2108190a6127783f8f635fc completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:27 p.m.