Triple

T15322346
Position Surface form Disambiguated ID Type / Status
Subject Innovative Research Universities E366321 entity
Predicate hasAbbreviation P43 FINISHED
Object IRU
IRU is a network of Australian universities focused on innovative, research-intensive education and collaboration.
E1150147 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: IRU | Statement: [Innovative Research Universities, hasAbbreviation, IRU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IRU
Context triple: [Innovative Research Universities, hasAbbreviation, IRU]
  • A. IRU
    IRU is the abbreviation for the International Romani Union, a global organization representing the interests and rights of Romani people.
  • B. IRI
    IRI (Industrial Research Institute) is a U.S.-based association of industrial and service companies focused on advancing innovation, research, and development management practices.
  • C. iru
    iru is the ISO 639-3 code for the Irula language, a Dravidian language spoken by the Irula people of southern India.
  • D. IRG
    IRG is the commonly used abbreviation for the International Rice Genebank, a major global repository for conserving rice genetic diversity.
  • E. IRIA
    IRIA (Institut de Recherche en Informatique et en Automatique) was the original French national research institute for computer science and automation, later becoming INRIA, and played a key role in early networking and informatics research.
  • 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: IRU
Triple: [Innovative Research Universities, hasAbbreviation, IRU]
Generated description
IRU is a network of Australian universities focused on innovative, research-intensive education and collaboration.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: IRU
Target entity description: IRU is a network of Australian universities focused on innovative, research-intensive education and collaboration.
  • A. IRU
    IRU is the abbreviation for the International Romani Union, a global organization representing the interests and rights of Romani people.
  • B. IRI
    IRI (Industrial Research Institute) is a U.S.-based association of industrial and service companies focused on advancing innovation, research, and development management practices.
  • C. iru
    iru is the ISO 639-3 code for the Irula language, a Dravidian language spoken by the Irula people of southern India.
  • D. IRG
    IRG is the commonly used abbreviation for the International Rice Genebank, a major global repository for conserving rice genetic diversity.
  • E. IRIA
    IRIA (Institut de Recherche en Informatique et en Automatique) was the original French national research institute for computer science and automation, later becoming INRIA, and played a key role in early networking and informatics research.
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dd460288190b5c41f0a0aeee949 completed April 16, 2026, 1:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef8aaef608190bd3ec9fdd215afbb completed May 9, 2026, 9:04 a.m.
NEDg Description generation batch_69fefa435efc81908c1e88267e745cdd completed May 9, 2026, 9:11 a.m.
NED2 Entity disambiguation (via description) batch_69fefb2ee9108190b3d8633cc9713c7b completed May 9, 2026, 9:15 a.m.
Created at: April 10, 2026, 3:16 a.m.