Triple

T22112855
Position Surface form Disambiguated ID Type / Status
Subject Sun Van E546459 entity
Predicate relatedTo P37 FINISHED
Object Sun Link NE NERFINISHED

How this triple was built (2 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: Sun Link | Statement: [Sun Van, relatedTo, Sun Link]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sun Link
Context triple: [Sun Van, relatedTo, Sun Link]
  • A. Sun Link chosen
    Sun Link is a modern streetcar system serving downtown Tucson, Arizona, and nearby districts as part of the city’s public transit network.
  • B. Skylink
    Skylink is an automated people mover system that transports passengers between terminals at Dallas/Fort Worth International Airport.
  • C. NovaLink
    NovaLink is an IBM Power Systems virtualization management interface that streamlines the deployment and control of virtual machines and resources on Power hardware.
  • D. Nitelink
    Nitelink is Dublin’s late-night bus service network, providing after-hours public transport on key routes across the city and suburbs.
  • E. U Link
    U Link is a successor student-focused service platform that continues and modernizes the functions previously provided under the name University Link.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e38b3848190ac3a4fa97d56e65a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1294ae7608190901745384a023bab completed April 28, 2026, 9:40 p.m.
Created at: April 16, 2026, 8:31 p.m.