Triple

T8876187
Position Surface form Disambiguated ID Type / Status
Subject Green Line (SEPTA) E211290 entity
Predicate hasRoute P4374 FINISHED
Object Route 36 E38584 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: Route 36 | Statement: [Green Line (SEPTA), hasRoute, Route 36]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Route 36
Context triple: [Green Line (SEPTA), hasRoute, Route 36]
  • A. Route 36 chosen
    Route 36 is a SEPTA subway–surface trolley line in Philadelphia that provides light rail service between Center City and Southwest Philadelphia.
  • B. Route 36
    Route 36 is a major New Jersey state highway that runs through coastal Monmouth County, providing access to communities such as Sandy Hook and other nearby shore areas.
  • C. Route 31
    Route 31 is a major north–south state highway in New Jersey that connects several central and northwestern communities, serving as a key regional transportation corridor.
  • D. Route 38
    Route 38 is a major east–west state highway in southern New Jersey that serves as a key commercial and commuter corridor through Cherry Hill and surrounding communities.
  • E. Route 38
    Route 38 is a state highway in Massachusetts that serves as a regional connector through several communities north of Boston.
  • 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_69ca838e78748190934d82db3104f855 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc61472cc081909e51b4a35a20ef43 completed April 1, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc1c641048190aabbc10f461099f4 completed April 3, 2026, 1:33 p.m.
Created at: March 30, 2026, 6:52 p.m.