Triple

T1074797
Position Surface form Disambiguated ID Type / Status
Subject San Francisco Muni E23810 entity
Predicate usesTicketingSystem P1740 FINISHED
Object Clipper
Clipper is a reloadable contactless smart card system used for paying fares on public transit across the San Francisco Bay Area.
 E123351 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: Clipper | Statement: [San Francisco Muni, usesTicketingSystem, Clipper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Clipper
Context triple: [San Francisco Muni, usesTicketingSystem, Clipper]
  • A. Cutty Sark
    Cutty Sark is a famous 19th-century British clipper ship preserved as a museum ship and historic landmark in London.
  • B. Seabreeze
    Seabreeze was a former neighboring city to Daytona Beach, Florida, that was eventually incorporated into the larger Daytona Beach municipality.
  • C. Carris
    Carris is the main public transport company in Lisbon, Portugal, operating the city's buses, trams, and certain historic lifts.
  • D. Argosy
    Argosy is a British pulp magazine best known for publishing adventure and genre fiction during the early to mid-20th century.
  • E. Klain
    Klain is the surname of Ron Klain, an American attorney and political operative who served as White House Chief of Staff under President Joe Biden.
  • 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: Clipper
Triple: [San Francisco Muni, usesTicketingSystem, Clipper]
Generated description
Clipper is a reloadable contactless smart card system used for paying fares on public transit across the San Francisco Bay Area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Clipper
Target entity description: Clipper is a reloadable contactless smart card system used for paying fares on public transit across the San Francisco Bay Area.
  • A. Cutty Sark
    Cutty Sark is a famous 19th-century British clipper ship preserved as a museum ship and historic landmark in London.
  • B. Seabreeze
    Seabreeze was a former neighboring city to Daytona Beach, Florida, that was eventually incorporated into the larger Daytona Beach municipality.
  • C. Carris
    Carris is the main public transport company in Lisbon, Portugal, operating the city's buses, trams, and certain historic lifts.
  • D. Argosy
    Argosy is a British pulp magazine best known for publishing adventure and genre fiction during the early to mid-20th century.
  • E. Klain
    Klain is the surname of Ron Klain, an American attorney and political operative who served as White House Chief of Staff under President Joe Biden.
  • 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_69a493f1ddf48190a99d54b00e99f8ce completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b92cbfd481909e2f928c1d06ebaa completed March 1, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac42a9af14819091d4f2578c6b1c02 completed March 7, 2026, 3:22 p.m.
NEDg Description generation batch_69ac434b7ea081909d5608831e29b5a9 completed March 7, 2026, 3:24 p.m.
NED2 Entity disambiguation (via description) batch_69ac43b393748190a5fa81b7ab7fa911 completed March 7, 2026, 3:26 p.m.
Created at: March 1, 2026, 7:42 p.m.