Triple

T7633090
Position Surface form Disambiguated ID Type / Status
Subject Знање и јединство E172804 entity
Predicate motoOf P77447 FINISHED
Object Универзитет у Београду E32111 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: Универзитет у Београду | Statement: [Знање и јединство, motoOf, Универзитет у Београду]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Универзитет у Београду
Context triple: [Знање и јединство, motoOf, Универзитет у Београду]
  • A. University of Belgrade chosen
    The University of Belgrade is a major public research university in Serbia and one of the oldest and largest higher education institutions in the Balkans.
  • B. University of Niš
    The University of Niš is a major public higher education and research institution located in the city of Niš, Serbia.
  • C. University of Novi Sad
    The University of Novi Sad is a major public research university in Serbia and one of the largest educational and scientific centers in Central and Southeast Europe.
  • D. University of Pristina
    The University of Pristina is a major public higher education and research institution located in Pristina, the capital of Kosovo.
  • E. University of Montenegro
    The University of Montenegro is the largest and oldest public higher education and research institution in Montenegro, offering a wide range of academic programs across multiple faculties.
  • 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: motoOf
Context triple: [Знање и јединство, motoOf, Универзитет у Београду]
  • A. vahanaOf
    Indicates that one entity serves as the vehicle, mount, or means of transportation for another entity.
  • B. motorizedUse
    Indicates that an entity is used or operated by means of a motor or engine, rather than by human or animal power.
  • C. rideModel
    Indicates that one entity is a specific model or type designation of a ride associated with another entity.
  • D. mainVehicle
    Indicates that one vehicle is the primary or most important vehicle associated with a given entity or context.
  • E. intendedVehicle
    Indicates that one entity is the vehicle that another entity plans or is meant to use.
  • 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_69c69952849881908fdcea7a93bfc307 completed March 27, 2026, 2:50 p.m.
NER Named-entity recognition batch_69c6faa5f4f08190a7e5259a1b6fb576 completed March 27, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8a2159cd0819085bfdb8c7694077b completed March 29, 2026, 3:52 a.m.
PD Predicate disambiguation batch_69c6f4e8cadc8190b7977fcd213954dd completed March 27, 2026, 9:21 p.m.
PDg Predicate description generation batch_69c6f574d8a8819095749518dad13791 completed March 27, 2026, 9:24 p.m.
Created at: March 27, 2026, 3:57 p.m.