Triple

T21105596
Position Surface form Disambiguated ID Type / Status
Subject Jane Withers E520034 entity
Predicate familyName P18 FINISHED
Object Withers
Withers is an English-origin surname borne by various notable individuals across fields such as entertainment, sports, and politics.
E1307870 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: Withers | Statement: [Jane Withers, familyName, Withers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Withers
Context triple: [Jane Withers, familyName, Withers]
  • A. Bracewell
    Bracewell is a surname most notably associated with Ronald N. Bracewell, an influential Australian-born radio astronomer and electrical engineer.
  • B. Pick Withers
    Pick Withers is an English drummer best known as the original drummer for the rock band Dire Straits.
  • C. Sidley
    Sidley is a residential suburb and village forming part of the seaside town of Bexhill-on-Sea in East Sussex, England.
  • D. Verrilli
    Verrilli is the surname of Donald B. Verrilli Jr., a prominent American lawyer who served as Solicitor General of the United States.
  • E. Latham
    Latham is a residential suburb in the Belconnen district of Canberra, in the Australian Capital Territory.
  • 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: Withers
Triple: [Jane Withers, familyName, Withers]
Generated description
Withers is an English-origin surname borne by various notable individuals across fields such as entertainment, sports, and politics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Withers
Target entity description: Withers is an English-origin surname borne by various notable individuals across fields such as entertainment, sports, and politics.
  • A. Bracewell
    Bracewell is a surname most notably associated with Ronald N. Bracewell, an influential Australian-born radio astronomer and electrical engineer.
  • B. Pick Withers chosen
    Pick Withers is an English drummer best known as the original drummer for the rock band Dire Straits.
  • C. Sidley
    Sidley is a residential suburb and village forming part of the seaside town of Bexhill-on-Sea in East Sussex, England.
  • D. Verrilli
    Verrilli is the surname of Donald B. Verrilli Jr., a prominent American lawyer who served as Solicitor General of the United States.
  • E. Latham
    Latham is a residential suburb in the Belconnen district of Canberra, in the Australian Capital Territory.
  • F. None of above.

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_69e0b509a318819092fbbcb21d1fe603 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e71b62301c819082cfc6cb3cd11c8c completed April 21, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a095a670d188190988befc0103ca4ec completed May 17, 2026, 6:04 a.m.
NEDg Description generation batch_6a095c4b5ad8819093e5c0de866be84b completed May 17, 2026, 6:12 a.m.
NED2 Entity disambiguation (via description) batch_6a095cda3c8081908d85b3da4fc1c06f completed May 17, 2026, 6:14 a.m.
Created at: April 16, 2026, 2:53 p.m.