Triple

T10105566
Position Surface form Disambiguated ID Type / Status
Subject MD 202 E216310 entity
Predicate hasJunctionWith P1018 FINISHED
Object MD 704 E666553 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: MD 704 | Statement: [MD 202, hasJunctionWith, MD 704]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MD 704
Context triple: [MD 202, hasJunctionWith, MD 704]
  • A. MD 704 chosen
    MD 704 is a state highway in Maryland that serves as a key local connector route in the Washington, D.C. metropolitan area.
  • B. MD 214
    MD 214 is a major east–west state highway in Maryland that connects Washington, D.C. suburbs with communities in Prince George’s and Anne Arundel counties.
  • C. MD 450
    MD 450 is a state highway in Maryland that serves as an important east–west route connecting communities in the Annapolis and Washington, D.C. metropolitan areas.
  • D. MD 145
    MD 145 is a state highway in Maryland that serves as an east–west route connecting communities in Baltimore County.
  • E. MD 202
    MD 202 is a state highway in Maryland that connects communities in Prince George’s County, including the area near FedExField and the Capital Beltway.
  • 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_69ca83d039f08190b9d10363221c69fb completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd09dde888190bb550a3cd0b204fe completed April 2, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2cc0572e08190a8ef4d620ac27d88 completed April 5, 2026, 8:54 p.m.
Created at: March 30, 2026, 9:03 p.m.