Triple

T12844141
Position Surface form Disambiguated ID Type / Status
Subject Angela Beesley E307127 entity
Predicate spouse P13 FINISHED
Object Tim Starling
Tim Starling is a software engineer best known for his long-time work as a MediaWiki developer and contributor to the Wikimedia Foundation’s technical infrastructure.
E1006078 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: Tim Starling | Statement: [Angela Beesley, spouse, Tim Starling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tim Starling
Context triple: [Angela Beesley, spouse, Tim Starling]
  • A. Santos Irwin
    Santos Irwin is the child of American actor and clown Bill Irwin.
  • B. Jamie Oddie
    Jamie Oddie is best known as the husband of Australian actress Claudia Black, recognized for her roles in science fiction television and film.
  • C. Jeff Corwin
    Jeff Corwin is an American wildlife biologist and television host best known for his nature and animal conservation programs on channels like Animal Planet and Discovery.
  • D. Bob Irwin
    Bob Irwin is an Australian conservationist and wildlife expert best known as the father of Steve Irwin and the original founder of the Australia Zoo.
  • E. Clark Peterson
    Clark Peterson is a film producer best known for his work on the Academy Award–winning biographical drama "Monster" (2003).
  • 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: Tim Starling
Triple: [Angela Beesley, spouse, Tim Starling]
Generated description
Tim Starling is a software engineer best known for his long-time work as a MediaWiki developer and contributor to the Wikimedia Foundation’s technical infrastructure.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tim Starling
Target entity description: Tim Starling is a software engineer best known for his long-time work as a MediaWiki developer and contributor to the Wikimedia Foundation’s technical infrastructure.
  • A. Santos Irwin
    Santos Irwin is the child of American actor and clown Bill Irwin.
  • B. Jamie Oddie
    Jamie Oddie is best known as the husband of Australian actress Claudia Black, recognized for her roles in science fiction television and film.
  • C. Jeff Corwin
    Jeff Corwin is an American wildlife biologist and television host best known for his nature and animal conservation programs on channels like Animal Planet and Discovery.
  • D. Bob Irwin
    Bob Irwin is an Australian conservationist and wildlife expert best known as the father of Steve Irwin and the original founder of the Australia Zoo.
  • E. Clark Peterson
    Clark Peterson is a film producer best known for his work on the Academy Award–winning biographical drama "Monster" (2003).
  • 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96ff3a7208190b93f6292ed5efc07 completed April 10, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69b9fa40c8190bbc2c6ad22795de4 completed May 3, 2026, 12:49 a.m.
NEDg Description generation batch_69f69ca6358c8190bb076249864f81a8 completed May 3, 2026, 12:53 a.m.
NED2 Entity disambiguation (via description) batch_69f69dc8b86c81908557fa8538e942de completed May 3, 2026, 12:58 a.m.
Created at: April 9, 2026, 5:36 p.m.