Triple

T10966553
Position Surface form Disambiguated ID Type / Status
Subject Harding E259114 entity
Predicate hasNotableBearer P458 FINISHED
Object Luke Harding E229319 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: Luke Harding | Statement: [Harding, hasNotableBearer, Luke Harding]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luke Harding
Context triple: [Harding, hasNotableBearer, Luke Harding]
  • A. Luke Harding chosen
    Luke Harding is a British journalist and author known for his investigative reporting on Russia, espionage, and international affairs, including works that inspired the film "The Fifth Estate."
  • B. Jon Sopel
    Jon Sopel is a British journalist and broadcaster best known for his work as a BBC correspondent and news presenter.
  • C. Edward Luce
    Edward Luce is a British journalist and author best known as a senior columnist and commentator on U.S. politics and global affairs for the Financial Times.
  • D. James Marr
    James Marr is a relatively obscure individual whose primary distinction is sharing the surname associated with the better-known Marr family name.
  • E. Nick Davies
    Nick Davies is a British investigative journalist best known for exposing the News of the World phone-hacking scandal and his extensive work on media ethics and corruption.
  • 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_69d6aa88500c819097d7032ca578e74f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d77149c0448190a66322fa696fdbda completed April 9, 2026, 9:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d78156c48190a956dc22b9832bcb completed April 18, 2026, 12:59 a.m.
Created at: April 8, 2026, 9:24 p.m.