Triple

T18848756
Position Surface form Disambiguated ID Type / Status
Subject Prazeres E460984 entity
Predicate servedBy P82 FINISHED
Object Tram 28
Tram 28 is a historic yellow Lisbon tram route famous for its scenic ride through the city’s steep, narrow streets and major old-town landmarks.
 E1345986 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: Tram 28 | Statement: [Prazeres, servedBy, Tram 28]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tram 28
Context triple: [Prazeres, servedBy, Tram 28]
  • A. Tram 12
    Tram 12 is a major tram line in Geneva’s public transport system, connecting key neighborhoods and suburbs across the city.
  • B. Tram 15
    Tram 15 is a major tram line in Geneva’s public transport system, connecting key districts across the city and its suburbs.
  • C. Tram 17
    Tram 17 is a tram line in Geneva’s public transport system operated by the city’s transit authority.
  • D. Tram 14
    Tram 14 is a major tram line in Geneva’s public transport system, connecting key districts and suburbs within the city.
  • E. Tram 18
    Tram 18 is a tram line in Geneva’s public transport system that connects key districts within the city and its surrounding areas.
  • 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: Tram 28
Triple: [Prazeres, servedBy, Tram 28]
Generated description
Tram 28 is a historic yellow Lisbon tram route famous for its scenic ride through the city’s steep, narrow streets and major old-town landmarks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tram 28
Target entity description: Tram 28 is a historic yellow Lisbon tram route famous for its scenic ride through the city’s steep, narrow streets and major old-town landmarks.
  • A. Tram 12
    Tram 12 is a major tram line in Geneva’s public transport system, connecting key neighborhoods and suburbs across the city.
  • B. Tram 15
    Tram 15 is a major tram line in Geneva’s public transport system, connecting key districts across the city and its suburbs.
  • C. Tram 17
    Tram 17 is a tram line in Geneva’s public transport system operated by the city’s transit authority.
  • D. Tram 14
    Tram 14 is a major tram line in Geneva’s public transport system, connecting key districts and suburbs within the city.
  • E. Tram 18
    Tram 18 is a tram line in Geneva’s public transport system that connects key districts within the city and its surrounding areas.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5b8f079b881908759135c5e2619ee completed April 20, 2026, 5:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0567778ef08190af337b59cb345eed completed May 14, 2026, 6:11 a.m.
NEDg Description generation batch_6a056c57c32481908b14f6a830a0e3e9 completed May 14, 2026, 6:31 a.m.
NED2 Entity disambiguation (via description) batch_6a056cf897188190b46a7c662c639d88 completed May 14, 2026, 6:34 a.m.
Created at: April 10, 2026, 11:56 a.m.