Triple

T20234852
Position Surface form Disambiguated ID Type / Status
Subject PTH 101 E495622 entity
Predicate connectsWith P37 FINISHED
Object Route 180 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: Route 180 | Statement: [PTH 101, connectsWith, Route 180]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Route 180
Context triple: [PTH 101, connectsWith, Route 180]
  • A. Route 180 chosen
    Route 180 is a state highway designated as State Route 180, typically serving as a regional connector road within its state's transportation network.
  • B. Route 185
    Route 185 is a numbered roadway that serves as a connector within the regional highway network linked to Route 440.
  • C. Route 184
    Route 184 is a numbered roadway that serves as a connector within a regional highway network, linking to other major routes such as Route 440.
  • D. Route 160
    Route 160 is a regional transportation route that serves as a key roadway connection for the city of Lota in Chile’s Biobío Region.
  • E. Route 140
    Route 140 is a state highway in Massachusetts that runs generally north–south, connecting several cities and towns between New Bedford and the Franklin area.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6716995b88190a8514b41232b0e94 completed April 20, 2026, 6:33 p.m.
Created at: April 11, 2026, 11:40 p.m.