Triple

T18994624
Position Surface form Disambiguated ID Type / Status
Subject NC 96 E464777 entity
Predicate connectsTo P845 FINISHED
Object US 15 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: US 15 | Statement: [NC 96, connectsTo, US 15]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: US 15
Context triple: [NC 96, connectsTo, US 15]
  • A. US 15 chosen
    US 15 is a major north–south U.S. Highway running from New York to South Carolina, serving as an important regional route through several Mid-Atlantic and Southern states.
  • B. US 151
    US 151 is a United States highway running through Iowa and Wisconsin, serving as a major regional route connecting cities such as Cedar Rapids, Dubuque, and Madison.
  • C. US 17
    US 17 is a major north–south U.S. highway running along the southeastern United States, connecting Florida with several Atlantic coastal states.
  • D. US 19
    US 19 is a major north–south United States highway running from Florida to Pennsylvania, serving numerous cities and regions along the eastern part of the country.
  • E. U.S. 1
    U.S. 1 is a 1938 poetry collection by Muriel Rukeyser that blends documentary material and lyrical experimentation to address social and political issues of the Great Depression era.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d680dd2881908a72e732c6b25477 completed April 20, 2026, 7:32 a.m.
Created at: April 10, 2026, 12:01 p.m.