Triple

T13064892
Position Surface form Disambiguated ID Type / Status
Subject Susan Hunt E329295 entity
Predicate spouse P13 FINISHED
Object James Hunt E92832 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: James Hunt | Statement: [Susan Hunt, spouse, James Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Hunt
Context triple: [Susan Hunt, spouse, James Hunt]
  • A. James Hunt chosen
    James Hunt was a charismatic British Formula One driver who won the 1976 World Championship and became famous for his intense rivalry with Niki Lauda and his flamboyant lifestyle.
  • B. Damon Hill
    Damon Hill is a British former Formula One driver who won the 1996 World Drivers' Championship with Williams.
  • C. Nigel Mansell
    Nigel Mansell is a British former Formula One and IndyCar driver, renowned for winning the 1992 F1 World Championship and the 1993 CART title and for his aggressive, determined driving style.
  • D. Jim Clark
    Jim Clark was a British film editor renowned for his work on numerous acclaimed movies across several decades, including major Hollywood and British productions.
  • E. Jim Clark
    Jim Clark is an American entrepreneur and computer scientist best known for co-founding Netscape and Silicon Graphics, playing a pivotal role in the early commercial development of the internet and computer graphics.
  • 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_69d80771749c81909a6d9197b9504872 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d980e9bdfc81908eb90fb50597df64 completed April 10, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbe630808190a9a3481127bbaa86 completed May 3, 2026, 4:15 a.m.
Created at: April 9, 2026, 8:59 p.m.