Triple

T384893
Position Surface form Disambiguated ID Type / Status
Subject Transamerica Pyramid E8758 entity
Predicate formerOwner P347 FINISHED
Object Aegon
Aegon is a multinational life insurance, pensions, and asset management company headquartered in the Netherlands.
 E48778 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: Aegon | Statement: [Transamerica Pyramid, formerOwner, Aegon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Aegon
Context triple: [Transamerica Pyramid, formerOwner, Aegon]
  • A. Jaime
    Jaime is a given name of Spanish origin, commonly used as a form of James.
  • B. Ahlden
    Ahlden is a small municipality in Lower Saxony, Germany, historically known for the long confinement and death of Sophia Dorothea of Celle.
  • C. Geoffrey
    Geoffrey is a masculine given name of English origin, famously borne by pioneering computer scientist and AI researcher Geoffrey Hinton.
  • D. Julian Burnside
    Julian Burnside is an Australian barrister and human rights advocate renowned for his work defending refugees and speaking out on civil liberties and social justice.
  • E. Tribonian
    Tribonian was a prominent 6th-century Byzantine jurist and official under Emperor Justinian I, best known for leading the codification of Roman law that shaped European legal tradition for centuries.
  • 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: Aegon
Triple: [Transamerica Pyramid, formerOwner, Aegon]
Generated description
Aegon is a multinational life insurance, pensions, and asset management company headquartered in the Netherlands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Aegon
Target entity description: Aegon is a multinational life insurance, pensions, and asset management company headquartered in the Netherlands.
  • A. Jaime
    Jaime is a given name of Spanish origin, commonly used as a form of James.
  • B. Ahlden
    Ahlden is a small municipality in Lower Saxony, Germany, historically known for the long confinement and death of Sophia Dorothea of Celle.
  • C. Geoffrey
    Geoffrey is a masculine given name of English origin, famously borne by pioneering computer scientist and AI researcher Geoffrey Hinton.
  • D. Julian Burnside
    Julian Burnside is an Australian barrister and human rights advocate renowned for his work defending refugees and speaking out on civil liberties and social justice.
  • E. Tribonian
    Tribonian was a prominent 6th-century Byzantine jurist and official under Emperor Justinian I, best known for leading the codification of Roman law that shaped European legal tradition for centuries.
  • 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_69a2e7f47dd08190a4e294ccbbe46cd4 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec4345a48190a413261cba4eafd7 completed Feb. 28, 2026, 1:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3fe95c7088190a1538eecb2ac6955 completed March 1, 2026, 8:53 a.m.
NEDg Description generation batch_69a3fec1294c8190bff1dc2c8ec6bfb0 completed March 1, 2026, 8:54 a.m.
NED2 Entity disambiguation (via description) batch_69a3ff1db088819087542685fbad01ad completed March 1, 2026, 8:55 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.