Triple

T1741454
Position Surface form Disambiguated ID Type / Status
Subject Clipper card E38241 entity
Predicate usedOn P2367 FINISHED
Object Golden Gate Ferry E193027 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: Golden Gate Ferry | Statement: [Clipper card, usedOn, Golden Gate Ferry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Golden Gate Ferry
Context triple: [Clipper card, usedOn, Golden Gate Ferry]
  • A. San Francisco Bay Ferry
    San Francisco Bay Ferry is a public ferry service that operates passenger routes across the San Francisco Bay, connecting various waterfront cities and transit hubs in the Bay Area.
  • B. Golden Gate Transit chosen
    Golden Gate Transit is a regional public bus and ferry system serving the North Bay and San Francisco in California.
  • C. SamTrans
    SamTrans is the public bus and paratransit agency serving San Mateo County and parts of the San Francisco Bay Area.
  • D. Washington State Ferries
    Washington State Ferries is the largest ferry system in the United States, operating a network of passenger and vehicle routes across the waterways of Washington State.
  • E. Vallejo Ferry Terminal
    Vallejo Ferry Terminal is a waterfront transit hub in Vallejo, California, providing passenger ferry service across the San Francisco Bay.
  • 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_69a8862b01a48190ab47209063af82d9 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63c6d21c8190809bedaa798e2b14 completed March 6, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada0dbc7c081909d637c5a482389ef completed March 8, 2026, 4:16 p.m.
Created at: March 4, 2026, 7:30 p.m.