Triple

T2502598
Position Surface form Disambiguated ID Type / Status
Subject Metrolink E52497 entity
Predicate formerRollingStock P29565 FINISHED
Object T-68 tram
The T-68 tram was a type of light rail vehicle used on Greater Manchester’s Metrolink system in the UK before being replaced by newer models.
 E275296 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: T-68 tram | Statement: [Metrolink, formerRollingStock, T-68 tram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: T-68 tram
Context triple: [Metrolink, formerRollingStock, T-68 tram]
  • A. SL95 tram
    The SL95 tram is a high-floor, bi-directional tram model used in Oslo, Norway, known for its large capacity and operation on the city’s light rail and tram network.
  • B. LM-93 tram
    The LM-93 tram is a Russian-built light rail vehicle model commonly used in city tram and metrotram systems such as the Volgograd Metrotram.
  • C. SL79 tram
    The SL79 tram is a class of articulated light rail vehicles used for passenger service on the Oslo Tramway network in Norway.
  • D. M5000 tram
    The M5000 tram is a modern light-rail vehicle used across the Manchester Metrolink network as its primary fleet for urban passenger services.
  • E. Alstom Citadis tram
    The Alstom Citadis tram is a family of modern low-floor light rail vehicles widely used in urban tram networks around the world.
  • 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: T-68 tram
Triple: [Metrolink, formerRollingStock, T-68 tram]
Generated description
The T-68 tram was a type of light rail vehicle used on Greater Manchester’s Metrolink system in the UK before being replaced by newer models.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: T-68 tram
Target entity description: The T-68 tram was a type of light rail vehicle used on Greater Manchester’s Metrolink system in the UK before being replaced by newer models.
  • A. SL95 tram
    The SL95 tram is a high-floor, bi-directional tram model used in Oslo, Norway, known for its large capacity and operation on the city’s light rail and tram network.
  • B. LM-93 tram
    The LM-93 tram is a Russian-built light rail vehicle model commonly used in city tram and metrotram systems such as the Volgograd Metrotram.
  • C. SL79 tram
    The SL79 tram is a class of articulated light rail vehicles used for passenger service on the Oslo Tramway network in Norway.
  • D. M5000 tram
    The M5000 tram is a modern light-rail vehicle used across the Manchester Metrolink network as its primary fleet for urban passenger services.
  • E. Alstom Citadis tram
    The Alstom Citadis tram is a family of modern low-floor light rail vehicles widely used in urban tram networks around the world.
  • 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_69ab4957b3a88190adf968ae0c1b931c completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1cb4f6481908d4e0a1dc0d84d3c completed March 7, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69af2b8bc7708190a507136d1f9f34ca completed March 9, 2026, 8:20 p.m.
NEDg Description generation batch_69af51b3017c81908cfe771204bfdb27 completed March 9, 2026, 11:03 p.m.
NED2 Entity disambiguation (via description) batch_69af5215f6ec8190a4c1ac69d69b202d completed March 9, 2026, 11:04 p.m.
Created at: March 6, 2026, 9:46 p.m.