Triple

T17068440
Position Surface form Disambiguated ID Type / Status
Subject Linden station E414149 entity
Predicate distanceFrom P1299 FINISHED
Object Elizabeth station E418019 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: Elizabeth station | Statement: [Linden station, distanceFrom, Elizabeth station]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth station
Context triple: [Linden station, distanceFrom, Elizabeth station]
  • A. Elizabeth station chosen
    Elizabeth station is a key New Jersey Transit rail stop in Elizabeth, New Jersey, providing commuter access along major regional routes including the busy Northeast Corridor.
  • B. Elizabeth station
    Elizabeth station is a railway station serving the suburb of Elizabeth in Adelaide, South Australia, providing commuter rail services on the Gawler line.
  • C. Kent Station
    Kent Station is the main railway station in Cork, Ireland, serving as a key hub for regional and intercity train services.
  • D. Kent Station
    Kent Station is a commuter rail station in Kent, Washington, served by Sound Transit’s Sounder South Line and integrated with local bus and park-and-ride facilities.
  • E. Robert Street Station
    Robert Street Station is a light rail stop in Saint Paul, Minnesota, serving passengers on the METRO Green Line.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbbeb2a48190a733a4cc829c16de completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a015fbb89fc81908d2355d36ea2469e completed May 11, 2026, 4:48 a.m.
Created at: April 10, 2026, 5:34 a.m.