Triple

T15554216
Position Surface form Disambiguated ID Type / Status
Subject Muni Metro lines E370826 entity
Predicate serves P98 FINISHED
Object Sunset Tunnel E545885 NE FINISHED

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: Sunset Tunnel | Statement: [Muni Metro lines, serves, Sunset Tunnel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sunset Tunnel
Context triple: [Muni Metro lines, serves, Sunset Tunnel]
  • A. Sunset Tunnel chosen
    Sunset Tunnel is a rail tunnel in San Francisco that carries Muni Metro light rail trains beneath the hilly terrain between the Duboce Triangle and Inner Sunset neighborhoods.
  • B. Summit Tunnel
    Summit Tunnel is a historic railroad tunnel driven through the Sierra Nevada in California, notable for its challenging 19th-century construction as part of the First Transcontinental Railroad.
  • C. Homer Tunnel
    Homer Tunnel is a road tunnel in New Zealand’s Fiordland that provides critical access through the mountains on the route to Milford Sound.
  • D. Zuzu Angel Tunnel
    Zuzu Angel Tunnel is a major road tunnel in Rio de Janeiro, Brazil, named in honor of the Brazilian fashion designer and political activist Zuzu Angel.
  • E. Bopeep Tunnel
    Bopeep Tunnel is a railway tunnel in East Sussex, England, carrying the Tonbridge–Hastings line through the coastal cliffs near St Leonards.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a96c0c88190808f68601a36b506 completed April 16, 2026, 2:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff456209288190aba6debd434af741 completed May 9, 2026, 2:32 p.m.
Created at: April 10, 2026, 4:09 a.m.