Triple

T15657035
Position Surface form Disambiguated ID Type / Status
Subject CRUSA E376468 entity
Predicate serves P98 FINISHED
Object Maryland E707 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: Maryland | Statement: [CRUSA, serves, Maryland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maryland
Context triple: [CRUSA, serves, Maryland]
  • A. Maryland chosen
    Maryland is a Mid-Atlantic U.S. state known for its Chesapeake Bay shoreline, colonial history, and proximity to the nation’s capital.
  • B. Maryland
    Maryland is a small village in Otsego County, New York, known primarily as a rural residential community in the central part of the state.
  • C. Maryland
    Maryland is a mixed residential and commercial neighborhood in Lagos, Nigeria, known for its strategic location, busy traffic junctions, and proximity to major business and transport hubs.
  • D. Maryland and Delaware
    Maryland and Delaware are two neighboring Mid-Atlantic U.S. states on the East Coast, known respectively for the Chesapeake Bay and the city of Baltimore, and for its Atlantic beaches and role as the nation’s first state to ratify the Constitution.
  • E. Virginia
    Virginia is a character in the classic French farce "Il cappello di paglia di Firenze" ("The Florentine Straw Hat"), around whom part of the play’s romantic and comedic misunderstandings revolve.
  • 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef1f83c8190bbf65eed162cbd55 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82e921e48190b5b5f4006ad65844 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:15 a.m.