Triple

T3054809
Position Surface form Disambiguated ID Type / Status
Subject Aarhus University E60454 entity
Predicate abbreviation P43 FINISHED
Object AU
Aarhus University (AU) is a major public research university in Aarhus, Denmark, known for its broad range of academic programs and strong international profile.
E323675 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: AU | Statement: [Aarhus University, abbreviation, AU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AU
Context triple: [Aarhus University, abbreviation, AU]
  • A. AU
    AU is the commonly used abbreviation for the African Union, a continental organization that promotes political and economic cooperation among African states.
  • B. AUD
    AUD is the stock ticker symbol for Audacy, Inc., a major American audio and radio broadcasting company.
  • C. Australia
    Australia is a large island continent and sovereign country in the Southern Hemisphere, known for its unique wildlife, diverse landscapes, and major cities such as Sydney and Melbourne.
  • D. Australia/Sydney
    Australia/Sydney is the IANA time zone identifier representing the local civil time for Sydney, Australia, including its daylight saving transitions.
  • E. ANZ
    ANZ is the ICAO airline designator used to identify Air New Zealand in international aviation operations.
  • 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: AU
Triple: [Aarhus University, abbreviation, AU]
Generated description
Aarhus University (AU) is a major public research university in Aarhus, Denmark, known for its broad range of academic programs and strong international profile.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AU
Target entity description: Aarhus University (AU) is a major public research university in Aarhus, Denmark, known for its broad range of academic programs and strong international profile.
  • A. AU
    AU is the commonly used abbreviation for the African Union, a continental organization that promotes political and economic cooperation among African states.
  • B. AUD
    AUD is the stock ticker symbol for Audacy, Inc., a major American audio and radio broadcasting company.
  • C. Australia
    Australia is a large island continent and sovereign country in the Southern Hemisphere, known for its unique wildlife, diverse landscapes, and major cities such as Sydney and Melbourne.
  • D. Australia/Sydney
    Australia/Sydney is the IANA time zone identifier representing the local civil time for Sydney, Australia, including its daylight saving transitions.
  • E. ANZ
    ANZ is the ICAO airline designator used to identify Air New Zealand in international aviation operations.
  • 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_69ad8578137c81908259dcb27c7d6d7c completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ad9bf6b9948190bc957bfd1579c471 completed March 8, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1ef03425c8190a44486ab563c210f completed March 11, 2026, 10:38 p.m.
NEDg Description generation batch_69b1f2d6e2008190adad44758e2d4766 completed March 11, 2026, 10:55 p.m.
NED2 Entity disambiguation (via description) batch_69b1f34005c88190817c40dc30f99f14 completed March 11, 2026, 10:57 p.m.
Created at: March 8, 2026, 3:02 p.m.