Triple

T4688715
Position Surface form Disambiguated ID Type / Status
Subject SL buses E103981 entity
Predicate brand P1500 FINISHED
Object SL
SL is the public transport authority and brand responsible for operating and coordinating buses, metro, and other transit services in the Stockholm region of Sweden.
 E103978 NE FINISHED

How this triple was built (4 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: SL | Statement: [SL buses, brand, SL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SL
Context triple: [SL buses, brand, SL]
  • A. SL
    The Mercedes-Benz SL is a long-running line of luxury grand touring roadsters renowned for combining high performance with elegant design and advanced technology.
  • B. SL
    SL is the vehicle registration code used for the Austrian municipality of Anif in the state of Salzburg.
  • C. SL
    SL is a German vehicle registration code used on license plates to identify cars registered in the Saalekreis district of Saxony-Anhalt.
  • D. SL
    SL is the IATA airline designator code assigned to SAS Ireland, a subsidiary carrier of Scandinavian Airlines.
  • E. SL
    SL is a mid-range trim level designation used by Holden for certain Torana models, offering additional comfort and convenience features over the base variants.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: SL
Triple: [SL buses, brand, SL]
Generated description
SL is the public transport authority and brand responsible for operating and coordinating buses, metro, and other transit services in the Stockholm region of Sweden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SL
Target entity description: SL is the public transport authority and brand responsible for operating and coordinating buses, metro, and other transit services in the Stockholm region of Sweden.
  • A. SL chosen
    SL is the public transport authority and brand responsible for operating and coordinating the mass transit system in the Stockholm region of Sweden.
  • B. SL
    SL is the IATA airline designator code assigned to SAS Ireland, a subsidiary carrier of Scandinavian Airlines.
  • C. SL
    SL is a German vehicle registration code used on license plates to identify cars registered in the Saalekreis district of Saxony-Anhalt.
  • D. SL
    SL is the vehicle registration code used for the Austrian municipality of Anif in the state of Salzburg.
  • E. SL
    SL is a UK postcode area covering Slough and surrounding parts of Berkshire and nearby counties.
  • F. None of above.

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_69bd43df91f481908e9add1b617b60ef completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd6399621881909aa8ffb1c27284e9 completed March 20, 2026, 3:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69be105a709c819083504fe1dc1612d8 completed March 21, 2026, 3:28 a.m.
NEDg Description generation batch_69be1278af588190832bcb037d18aa8f completed March 21, 2026, 3:37 a.m.
NED2 Entity disambiguation (via description) batch_69be12d51db08190aca8c36972ea6e4e completed March 21, 2026, 3:39 a.m.
Created at: March 20, 2026, 1:16 p.m.