Triple

T2883231
Position Surface form Disambiguated ID Type / Status
Subject Sydney Roosters E59443 entity
Predicate trainingBaseLocation P38230 FINISHED
Object Sydney E8462 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: Sydney | Statement: [Sydney Roosters, trainingBaseLocation, Sydney]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sydney
Context triple: [Sydney Roosters, trainingBaseLocation, Sydney]
  • A. Sydney chosen
    Sydney is Australia's largest and most populous city, renowned for its iconic harbour, Opera House, and Harbour Bridge.
  • B. Melbourne
    Melbourne is a major Australian city known for its vibrant arts scene, diverse culture, and status as a leading center for sports and education.
  • C. Melbourne
    Melbourne is a historic market town in Derbyshire, England, known for its Georgian architecture and the notable Melbourne Hall and gardens.
  • D. Melbourn
    Melbourn is a village and civil parish in South Cambridgeshire, England, known for its historic architecture and rural community character.
  • E. Brisbane
    Brisbane is a small city in northern San Mateo County, California, located just south of San Francisco on the lower slopes of San Bruno Mountain.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: trainingBaseLocation
Context triple: [Sydney Roosters, trainingBaseLocation, Sydney]
  • A. trainingBase
    Indicates that one entity serves as the training base, site, or facility where another entity receives training or instruction.
  • B. trainingBaseRegion chosen
    Indicates the geographic region where an entity’s training activities or training base is located or conducted.
  • C. trainingFacilityLocation
    Indicates the place or site where a training facility is situated or operates.
  • D. springTrainingLocation
    Indicates the location where an entity conducts its spring training activities.
  • E. trainingGround
    Indicates a location or context where entities engage in practice, drills, or preparation activities to develop or improve skills.
  • F. None of above.

Provenance (4 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_69ab4ac739188190a112f42a5a69c951 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abe02c238881908f7a349563c388bf completed March 7, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69b3544e32a0819087d554982f443b1d completed March 13, 2026, 12:03 a.m.
PD Predicate disambiguation batch_69abdd15cbf08190bf7fea5ea516848a completed March 7, 2026, 8:08 a.m.
Created at: March 6, 2026, 10:03 p.m.