Triple

T33845815
Position Surface form Disambiguated ID Type / Status
Subject Kensington campus E867475 entity
Predicate hasSportsOrganisation P103892 FINISHED
Object UNSW Sport
UNSW Sport is the sports and recreation organisation of the University of New South Wales, coordinating student and community sporting clubs, competitions, and fitness programs.
 E2069842 NE FINISHED

How this triple was built (3 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: UNSW Sport | Statement: [Kensington campus, hasSportsOrganisation, UNSW Sport]
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: UNSW Sport
Triple: [Kensington campus, hasSportsOrganisation, UNSW Sport]
Generated description
UNSW Sport is the sports and recreation organisation of the University of New South Wales, coordinating student and community sporting clubs, competitions, and fitness programs.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasSportsOrganisation
Context triple: [Kensington campus, hasSportsOrganisation, UNSW Sport]
  • A. sportOrganizationManaged
    Indicates that one entity is responsible for directing, operating, or overseeing the activities and affairs of a sports-related organization.
  • B. hasSportsClubs chosen
    Indicates that an entity possesses, hosts, or is associated with one or more sports clubs.
  • C. containsSportsTeam
    Indicates that one entity (typically a location or organization) has a sports team as part of it or within its boundaries.
  • D. hasAthleticTeamType
    Indicates that an entity’s athletic team participates in or is classified under a specific type or category of sport or competition.
  • E. leagueOrganization
    Indicates that an organization is responsible for running, governing, or officially managing a sports league or competitive league.
  • F. None of above.

Provenance (6 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_69f349937b648190a34ada70f6a2b534 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69fdfbafe32081909c62653ff4fc155c completed May 8, 2026, 3:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a366eb1b49881908d3c0c5904d30fd3 completed June 20, 2026, 10:42 a.m.
NEDg Description generation batch_6a366f86630c81908530464a68656b76 completed June 20, 2026, 10:46 a.m.
NED2 Entity disambiguation (via description) batch_6a36710d8bf081909ea6d06eca8ebdda completed June 20, 2026, 10:53 a.m.
PD Predicate disambiguation batch_69fdf64db4a881908f8250e24ae3cefb completed May 8, 2026, 2:42 p.m.
Created at: May 1, 2026, 1:47 a.m.