Triple

T23114784
Position Surface form Disambiguated ID Type / Status
Subject First South Yorkshire E576718 entity
Predicate brandOf P1500 FINISHED
Object First Bus 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: First Bus | Statement: [First South Yorkshire, brandOf, First Bus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: First Bus
Context triple: [First South Yorkshire, brandOf, First Bus]
  • A. First Bus chosen
    First Bus is a major UK bus operator providing local and regional public transport services in numerous towns and cities.
  • B. National Bus Company
    The National Bus Company was a large state-owned operator that oversaw most local and regional bus services in England and Wales from the late 1960s until its privatization in the 1980s.
  • C. Dan Bus Company
    Dan Bus Company is a major Israeli public transportation operator, best known for running extensive bus services in the Tel Aviv metropolitan area.
  • D. Golden Arrow Bus Services
    Golden Arrow Bus Services is a major public bus operator in Cape Town, South Africa, providing commuter transport across the city and its surrounding suburbs.
  • E. Carris bus lines
    Carris bus lines are the public bus services operating in Lisbon, Portugal, connecting neighborhoods such as Graça with the rest of the city.
  • 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_69e245f6c2e881909a228fdcfeb7c7d3 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18e11e9dc819093c569f388ffd46b completed April 29, 2026, 4:50 a.m.
Created at: April 17, 2026, 3:59 p.m.