Triple

T7051648
Position Surface form Disambiguated ID Type / Status
Subject G. I. Taylor E163980 entity
Predicate givenName P17 FINISHED
Object Geoffrey E28362 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: Geoffrey | Statement: [G. I. Taylor, givenName, Geoffrey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geoffrey
Context triple: [G. I. Taylor, givenName, Geoffrey]
  • A. Geoffrey chosen
    Geoffrey is a masculine given name of English origin, famously borne by pioneering computer scientist and AI researcher Geoffrey Hinton.
  • B. Geoffrey the Handsome
    Geoffrey the Handsome was a 12th-century Count of Anjou and Duke of Normandy, notable as the husband of Empress Matilda and the father of King Henry II of England, founding the Plantagenet dynasty.
  • C. Ranulph
    Ranulph is the given name of Sir Ranulph Fiennes, the renowned British explorer and adventurer known for his polar expeditions and endurance feats.
  • D. Godfrey
    Godfrey is the given name of the influential British mathematician G. H. Hardy, renowned for his work in number theory and mathematical analysis.
  • E. Godfrey
    Godfrey is an American comedian and actor known for his stand-up work and film roles, including a prominent appearance in the comedy movie "Soul Plane."
  • 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_69c68861678881909961ddf4d779f750 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e2500570819087200013d859cfe6 completed March 27, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c78891bc5081909db384a35b45df4a completed March 28, 2026, 7:51 a.m.
Created at: March 27, 2026, 2:37 p.m.