Triple

T6173053
Position Surface form Disambiguated ID Type / Status
Subject Scott Dixon E137748 entity
Predicate spouse P13 FINISHED
Object Emma Davies-Dixon
Emma Davies-Dixon is the wife of New Zealand IndyCar champion Scott Dixon and a former Welsh distance runner and model.
E572969 NE FINISHED

How this triple was built (4 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: Emma Davies-Dixon | Statement: [Scott Dixon, spouse, Emma Davies-Dixon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emma Davies-Dixon
Context triple: [Scott Dixon, spouse, Emma Davies-Dixon]
  • A. May Davies
    May Davies was the mother of Romanian-born American actor and producer John Houseman.
  • B. Caroline Farrell
    Caroline Farrell is the original identity of Echo, the central protagonist in Joss Whedon’s science fiction TV series "Dollhouse."
  • C. Kimberlea Cloughley
    Kimberlea Cloughley is an American photographer best known for her marriage to actor Tommy Lee Jones.
  • D. Caroline Goodall
    Caroline Goodall is an English actress known for her roles in major films such as Schindler's List, Hook, and Cliffhanger.
  • E. Emma Soames
    Emma Soames is a British editor and writer, known for her work in magazines such as Saga and for being a granddaughter of Winston Churchill.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Emma Davies-Dixon
Triple: [Scott Dixon, spouse, Emma Davies-Dixon]
Generated description
Emma Davies-Dixon is the wife of New Zealand IndyCar champion Scott Dixon and a former Welsh distance runner and model.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Emma Davies-Dixon
Target entity description: Emma Davies-Dixon is the wife of New Zealand IndyCar champion Scott Dixon and a former Welsh distance runner and model.
  • A. May Davies
    May Davies was the mother of Romanian-born American actor and producer John Houseman.
  • B. Caroline Farrell
    Caroline Farrell is the original identity of Echo, the central protagonist in Joss Whedon’s science fiction TV series "Dollhouse."
  • C. Kimberlea Cloughley
    Kimberlea Cloughley is an American photographer best known for her marriage to actor Tommy Lee Jones.
  • D. Caroline Goodall
    Caroline Goodall is an English actress known for her roles in major films such as Schindler's List, Hook, and Cliffhanger.
  • E. Emma Soames
    Emma Soames is a British editor and writer, known for her work in magazines such as Saga and for being a granddaughter of Winston Churchill.
  • F. None of above. chosen

Provenance (5 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_69c008a68c508190a8d78245c865960e completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05d94c47481909745b2533926a1ca completed March 22, 2026, 9:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141b200788190bd8d968edba53e5f completed March 23, 2026, 1:35 p.m.
NEDg Description generation batch_69c148476d2481909da6cebc4f0422e2 completed March 23, 2026, 2:03 p.m.
NED2 Entity disambiguation (via description) batch_69c148c2be64819099170df84a904eb9 completed March 23, 2026, 2:05 p.m.
Created at: March 22, 2026, 4:18 p.m.