Triple

T546009
Position Surface form Disambiguated ID Type / Status
Subject AOC-in-C Fighter Command E12733 entity
Predicate positionHeldBy P8 FINISHED
Object Anthony Skingsley
Anthony Skingsley was a senior Royal Air Force officer who rose to high command during the late 20th century, overseeing key aspects of the UK's air defense.
 E71005 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: Anthony Skingsley | Statement: [AOC-in-C Fighter Command, positionHeldBy, Anthony Skingsley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Anthony Skingsley
Context triple: [AOC-in-C Fighter Command, positionHeldBy, Anthony Skingsley]
  • A. Lennox Cato
    Lennox Cato is a British antiques dealer and television expert best known for his appearances on the BBC’s "Antiques Roadshow."
  • B. Roland Caulder
    Roland Caulder is an actor known for his role in the film "The Iron Mask."
  • C. Garth
    Garth is a fictional character from the American prime-time television soap opera "Falcon Crest."
  • D. John Underhill
    John Underhill was a 17th-century English colonial soldier and militia leader in New England, known for his prominent and controversial role in early Native American conflicts.
  • E. Robert Black
    Robert Black is a relatively common personal name shared by multiple notable individuals across fields such as music, literature, and law.
  • 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: Anthony Skingsley
Triple: [AOC-in-C Fighter Command, positionHeldBy, Anthony Skingsley]
Generated description
Anthony Skingsley was a senior Royal Air Force officer who rose to high command during the late 20th century, overseeing key aspects of the UK's air defense.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Anthony Skingsley
Target entity description: Anthony Skingsley was a senior Royal Air Force officer who rose to high command during the late 20th century, overseeing key aspects of the UK's air defense.
  • A. Lennox Cato
    Lennox Cato is a British antiques dealer and television expert best known for his appearances on the BBC’s "Antiques Roadshow."
  • B. Roland Caulder
    Roland Caulder is an actor known for his role in the film "The Iron Mask."
  • C. Garth
    Garth is a fictional character from the American prime-time television soap opera "Falcon Crest."
  • D. John Underhill
    John Underhill was a 17th-century English colonial soldier and militia leader in New England, known for his prominent and controversial role in early Native American conflicts.
  • E. Robert Black
    Robert Black is a relatively common personal name shared by multiple notable individuals across fields such as music, literature, and law.
  • 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_69a49334226c81908b0ea1689ef6aa3f completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a498e150e88190b35b1bc7a376ca07 completed March 1, 2026, 7:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4efcc641c8190b9538069fa88db94 completed March 2, 2026, 2:02 a.m.
NEDg Description generation batch_69a4f0a7376081908eb2ebfeb731dab1 completed March 2, 2026, 2:06 a.m.
NED2 Entity disambiguation (via description) batch_69a4f103ab10819081675ccae0b210b5 completed March 2, 2026, 2:08 a.m.
Created at: March 1, 2026, 7:32 p.m.