Triple

T5248736
Position Surface form Disambiguated ID Type / Status
Subject AstraZeneca E118527 entity
Predicate foundedBy P104 FINISHED
Object Astra AB
Astra AB was a Swedish pharmaceutical company that became one of the predecessors of the global biopharmaceutical firm AstraZeneca.
 E505476 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: Astra AB | Statement: [AstraZeneca, foundedBy, Astra AB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Astra AB
Context triple: [AstraZeneca, foundedBy, Astra AB]
  • A. Saab AB
    Saab AB is a Swedish aerospace and defense company known for developing military aircraft, advanced defense systems, and security solutions.
  • B. Volvo Group
    Volvo Group is a Swedish multinational manufacturing company best known for producing trucks, buses, construction equipment, and marine and industrial engines.
  • C. Astrium
    Astrium was a major European aerospace company specializing in the design and manufacture of satellites, space systems, and launch vehicle components.
  • D. Aral AG
    Aral AG is a major German brand of fuel stations and petroleum products, widely recognized for its network of service stations across Germany.
  • E. Aegon N.V.
    Aegon N.V. is a multinational life insurance, pensions, and asset management company headquartered in the Netherlands.
  • 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: Astra AB
Triple: [AstraZeneca, foundedBy, Astra AB]
Generated description
Astra AB was a Swedish pharmaceutical company that became one of the predecessors of the global biopharmaceutical firm AstraZeneca.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Astra AB
Target entity description: Astra AB was a Swedish pharmaceutical company that became one of the predecessors of the global biopharmaceutical firm AstraZeneca.
  • A. Saab AB
    Saab AB is a Swedish aerospace and defense company known for developing military aircraft, advanced defense systems, and security solutions.
  • B. Volvo Group
    Volvo Group is a Swedish multinational manufacturing company best known for producing trucks, buses, construction equipment, and marine and industrial engines.
  • C. Astrium
    Astrium was a major European aerospace company specializing in the design and manufacture of satellites, space systems, and launch vehicle components.
  • D. Aral AG
    Aral AG is a major German brand of fuel stations and petroleum products, widely recognized for its network of service stations across Germany.
  • E. Aegon N.V.
    Aegon N.V. is a multinational life insurance, pensions, and asset management company headquartered in the Netherlands.
  • 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_69bd4468aacc8190a8196f71855cdf4f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b787b34819081af96de9355bb4f completed March 20, 2026, 4:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69bef83998f881909fef2746f5c496af completed March 21, 2026, 7:57 p.m.
NEDg Description generation batch_69befa746be88190a8d807317ab36430 completed March 21, 2026, 8:07 p.m.
NED2 Entity disambiguation (via description) batch_69befac54e8c8190986aca0f5591d04e completed March 21, 2026, 8:08 p.m.
Created at: March 20, 2026, 1:50 p.m.