Triple

T10532938
Position Surface form Disambiguated ID Type / Status
Subject Potrero Hill E248488 entity
Predicate servedBy P82 FINISHED
Object Muni bus lines E39999 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: Muni bus lines | Statement: [Potrero Hill, servedBy, Muni bus lines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Muni bus lines
Context triple: [Potrero Hill, servedBy, Muni bus lines]
  • A. Muni bus network chosen
    The Muni bus network is San Francisco’s citywide public transit system of buses and trolleybuses that provides comprehensive surface transportation across the city.
  • B. Muni Metro lines
    Muni Metro lines are a network of light rail routes in San Francisco that provide rapid transit service across the city as part of the San Francisco Municipal Railway system.
  • C. MUNI
    MUNI is the commonly used abbreviation for Masaryk University, a major public research university based in Brno, Czech Republic.
  • D. Muni Metro Market Street lines
    Muni Metro Market Street lines are a set of light rail routes in San Francisco that run in a subway beneath Market Street, forming the core of the city’s urban rail transit corridor.
  • E. Metro Bus
    Metro Bus is the primary public bus service network for Los Angeles County, providing extensive local and rapid transit across the region.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d50a19b59c8190b00db7d5813ad37d completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e471e9c8190b134249073b289bd completed April 10, 2026, 2:50 p.m.
Created at: April 6, 2026, 12:30 p.m.