Triple

T18849630
Position Surface form Disambiguated ID Type / Status
Subject Carris trams E461005 entity
Predicate notableRoute P22 FINISHED
Object Route 12E 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 12E | Statement: [Carris trams, notableRoute, Route 12E]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Route 12E
Context triple: [Carris trams, notableRoute, Route 12E]
  • A. Route 12E chosen
    Route 12E is a historic Lisbon tram line known for its short, scenic loop through the city’s old quarters in traditional yellow trams.
  • B. Route 122
    Route 122 is a state highway in Maine that serves as a short connector route between the cities of Auburn and New Gloucester.
  • C. Route 126
    Route 126 is a state highway in Massachusetts that runs through several communities, including the city of Framingham.
  • D. Route 112
    Route 112 is a major provincial highway in Quebec that runs through the Montreal area, serving as an important east–west transportation corridor connecting several communities.
  • E. Route 125
    Route 125 is a state highway in northeastern Massachusetts that runs through several communities north of Boston, serving as a key regional connector.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5b8f1abdc819081638ed384da191e completed April 20, 2026, 5:26 a.m.
Created at: April 10, 2026, 11:56 a.m.