Triple

T20882114
Position Surface form Disambiguated ID Type / Status
Subject Doe Avedon E514176 entity
Predicate spouse P13 FINISHED
Object Dan Matthews
Dan Matthews is known primarily as the husband of American model and actress Doe Avedon.
 E1458633 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: Dan Matthews | Statement: [Doe Avedon, spouse, Dan Matthews]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dan Matthews
Context triple: [Doe Avedon, spouse, Dan Matthews]
  • A. Don Matthews
    Don Matthews was a highly successful and influential Canadian Football League head coach, renowned for leading multiple teams to Grey Cup championships.
  • B. Daniel Matthews
    Daniel Matthews is a fictional character in the Saw horror film franchise, notably appearing as one of Jigsaw’s trapped victims in Saw II.
  • C. Scott Matthews
    Scott Matthews is an English singer-songwriter and guitarist known for his emotive vocals and atmospheric folk-rock compositions.
  • D. Stephen Matthews
    Stephen Matthews is a linguist known for his work on Cantonese and other Sinitic languages, as well as for co-authoring influential grammars and studies in language typology.
  • E. Joseph Matthews
    Joseph Matthews is a relatively obscure individual whose name is shared with multiple people, including authors and professionals, without a single widely recognized public figure dominating the name.
  • 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: Dan Matthews
Triple: [Doe Avedon, spouse, Dan Matthews]
Generated description
Dan Matthews is known primarily as the husband of American model and actress Doe Avedon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dan Matthews
Target entity description: Dan Matthews is known primarily as the husband of American model and actress Doe Avedon.
  • A. Don Matthews
    Don Matthews was a highly successful and influential Canadian Football League head coach, renowned for leading multiple teams to Grey Cup championships.
  • B. Daniel Matthews
    Daniel Matthews is a fictional character in the Saw horror film franchise, notably appearing as one of Jigsaw’s trapped victims in Saw II.
  • C. Scott Matthews
    Scott Matthews is an English singer-songwriter and guitarist known for his emotive vocals and atmospheric folk-rock compositions.
  • D. Stephen Matthews
    Stephen Matthews is a linguist known for his work on Cantonese and other Sinitic languages, as well as for co-authoring influential grammars and studies in language typology.
  • E. Joseph Matthews
    Joseph Matthews is a relatively obscure individual whose name is shared with multiple people, including authors and professionals, without a single widely recognized public figure dominating the name.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c67a33548190b0f5ba58b001d387 completed April 21, 2026, 12:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0927795af481909263097b879a49b4 completed May 17, 2026, 2:27 a.m.
NEDg Description generation batch_6a092836c24481908209bbf4816f0112 completed May 17, 2026, 2:30 a.m.
NED2 Entity disambiguation (via description) batch_6a092862d5c88190877df16632dd1b77 completed May 17, 2026, 2:30 a.m.
Created at: April 16, 2026, 12:46 p.m.