Triple

T2040149
Position Surface form Disambiguated ID Type / Status
Subject Rowan Williams E44723 entity
Predicate hasChild P369 FINISHED
Object Rhiannon Williams
Rhiannon Williams is a daughter of Rowan Williams, the former Archbishop of Canterbury and prominent theologian.
E230672 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: Rhiannon Williams | Statement: [Rowan Williams, hasChild, Rhiannon Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rhiannon Williams
Context triple: [Rowan Williams, hasChild, Rhiannon Williams]
  • A. Lindsay Brunnock
    Lindsay Brunnock is a British art director known for her work in film and television and for being married to actor and director Kenneth Branagh.
  • B. Christiana Evans
    Christiana Evans was the mother of the renowned Victorian novelist George Eliot (Mary Ann Evans).
  • C. Bethan Phillips
    Bethan Phillips was the wife of influential Welsh Protestant minister and preacher Martyn Lloyd-Jones.
  • D. Imogen Poots
    Imogen Poots is a British actress known for her versatile performances in films such as "Green Room," "28 Weeks Later," and "Need for Speed."
  • E. Rachael MacFarlane
    Rachael MacFarlane is an American voice actress and singer best known for her work on animated television series, including voicing Hayley Smith on "American Dad!"
  • 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: Rhiannon Williams
Triple: [Rowan Williams, hasChild, Rhiannon Williams]
Generated description
Rhiannon Williams is a daughter of Rowan Williams, the former Archbishop of Canterbury and prominent theologian.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rhiannon Williams
Target entity description: Rhiannon Williams is a daughter of Rowan Williams, the former Archbishop of Canterbury and prominent theologian.
  • A. Lindsay Brunnock
    Lindsay Brunnock is a British art director known for her work in film and television and for being married to actor and director Kenneth Branagh.
  • B. Christiana Evans
    Christiana Evans was the mother of the renowned Victorian novelist George Eliot (Mary Ann Evans).
  • C. Bethan Phillips
    Bethan Phillips was the wife of influential Welsh Protestant minister and preacher Martyn Lloyd-Jones.
  • D. Imogen Poots
    Imogen Poots is a British actress known for her versatile performances in films such as "Green Room," "28 Weeks Later," and "Need for Speed."
  • E. Rachael MacFarlane
    Rachael MacFarlane is an American voice actress and singer best known for her work on animated television series, including voicing Hayley Smith on "American Dad!"
  • 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_69a889159ec481908f9e4472d9f480c7 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb9533bd881909e3aecff7ddb5a8b completed March 7, 2026, 5:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae271399a08190946b315f439b9b2f completed March 9, 2026, 1:49 a.m.
NEDg Description generation batch_69ae2847a7e0819092026253e036bd1c completed March 9, 2026, 1:54 a.m.
NED2 Entity disambiguation (via description) batch_69ae28ce87c8819097e0b5dab045d9a1 completed March 9, 2026, 1:56 a.m.
Created at: March 4, 2026, 7:39 p.m.