Triple

T14773050
Position Surface form Disambiguated ID Type / Status
Subject Amtrak Downeaster E347183 entity
Predicate viaStation P64719 FINISHED
Object Saco station
Saco station is a passenger rail station in Saco, Maine, served by Amtrak’s Downeaster route between Boston and Brunswick.
E1119478 NE FINISHED

How this triple was built (4 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: Saco station | Statement: [Amtrak Downeaster, viaStation, Saco station]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saco station
Context triple: [Amtrak Downeaster, viaStation, Saco station]
  • A. Prujakan Station
    Prujakan Station is a railway station in Cirebon, Indonesia, serving as one of the city’s key stops for regional and intercity train services.
  • B. La Estrella station
    La Estrella station is the southern terminal station of Line A of the Medellín Metro system in Colombia.
  • C. Seymour station
    Seymour station is a small commuter rail stop in Seymour, Connecticut, served by Metro-North Railroad’s Waterbury Branch.
  • D. Legarda station
    Legarda station is an elevated rapid transit stop on Manila’s LRT Line 2 serving the Sampaloc area and nearby universities.
  • E. Cabitos station
    Cabitos station is a stop on Lima Metro’s Line 1 serving passengers in the southern part of Peru’s capital city.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Saco station
Triple: [Amtrak Downeaster, viaStation, Saco station]
Generated description
Saco station is a passenger rail station in Saco, Maine, served by Amtrak’s Downeaster route between Boston and Brunswick.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saco station
Target entity description: Saco station is a passenger rail station in Saco, Maine, served by Amtrak’s Downeaster route between Boston and Brunswick.
  • A. Prujakan Station
    Prujakan Station is a railway station in Cirebon, Indonesia, serving as one of the city’s key stops for regional and intercity train services.
  • B. La Estrella station
    La Estrella station is the southern terminal station of Line A of the Medellín Metro system in Colombia.
  • C. Seymour station
    Seymour station is a small commuter rail stop in Seymour, Connecticut, served by Metro-North Railroad’s Waterbury Branch.
  • D. Legarda station
    Legarda station is an elevated rapid transit stop on Manila’s LRT Line 2 serving the Sampaloc area and nearby universities.
  • E. Cabitos station
    Cabitos station is a stop on Lima Metro’s Line 1 serving passengers in the southern part of Peru’s capital city.
  • F. None of above. chosen

Provenance (5 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec81485e08190be35baafcf22b6f2 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cfd26fc81909fba39c8705437ed completed May 8, 2026, 4:19 p.m.
NEDg Description generation batch_69fe17fc37ec8190b2e9c786a5e7843e completed May 8, 2026, 5:06 p.m.
NED2 Entity disambiguation (via description) batch_69fe18786294819080ce5ee0d8af00c9 completed May 8, 2026, 5:08 p.m.
Created at: April 10, 2026, 1:31 a.m.