Triple

T8216991
Position Surface form Disambiguated ID Type / Status
Subject AL 21 E191957 entity
Predicate connectsTo P845 FINISHED
Object US 31 E249544 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: US 31 | Statement: [AL 21, connectsTo, US 31]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: US 31
Context triple: [AL 21, connectsTo, US 31]
  • A. US 31 chosen
    US 31 is a major north–south United States highway running through several Midwestern and Southern states, serving as an important regional transportation corridor.
  • B. US 41
    US 41 is a major north–south U.S. highway running from Miami, Florida, through the Midwest to the Upper Peninsula of Michigan near the Canadian border.
  • C. US 131
    US 131 is a north–south U.S. Highway in western Michigan that runs from the Indiana state line through cities such as Kalamazoo and Grand Rapids up toward the northern Lower Peninsula.
  • D. US 23
    US 23 is a major north–south United States highway running from Florida to Michigan, serving as an important regional transportation corridor.
  • E. US 61
    US 61 is a major north–south United States highway running along the Mississippi River corridor, linking New Orleans to the Upper Midwest.
  • 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_69ca82c8c054819087fedd9a5436b8a3 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb776f41108190bed1c6a8ddbea374 completed March 31, 2026, 7:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccedfb6f608190aebfa720b56325e5 completed April 1, 2026, 10:05 a.m.
Created at: March 30, 2026, 5:44 p.m.