Triple

T32818607
Position Surface form Disambiguated ID Type / Status
Subject Red Line (Washington Metro) stations E839370 entity
Predicate serveState P199506 FINISHED
Object Maryland NE NERFINISHED

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: Maryland | Statement: [Red Line (Washington Metro) stations, serveState, Maryland]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: serveState
Context triple: [Red Line (Washington Metro) stations, serveState, Maryland]
  • A. serviceToState
    Indicates a relationship where an entity provides service, assistance, or functional support to a state or governmental body.
  • B. serveAt
    Indicates that one entity provides service, work, or duties at a particular place, organization, or event.
  • C. hasServingState
    Indicates that an entity (such as a food or drink item) is associated with a particular state or condition in which it is served.
  • D. someServe
    Indicates that one entity serves, assists, or performs duties for another entity in some capacity.
  • E. isServed
    Indicates that one entity provides or delivers a service, product, or assistance to another entity.
  • F. None of above. chosen

Provenance (4 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_69f3493df9008190a8f5d843dcd77704 completed April 30, 2026, 12:21 p.m.
NER Named-entity recognition batch_69ff3fb2318c81908a46c2f513608935 completed May 9, 2026, 2:07 p.m.
PD Predicate disambiguation batch_69ff3e96dcc48190819f6204680d84aa completed May 9, 2026, 2:03 p.m.
PDg Predicate description generation batch_69ff3fb151008190bf8a90f9f1c5f0c8 completed May 9, 2026, 2:07 p.m.
Created at: May 1, 2026, 1:15 a.m.