Triple

T12954350
Position Surface form Disambiguated ID Type / Status
Subject Porto São Bento railway station E309971 entity
Predicate railwayStationCode P1289 FINISHED
Object PSE
PSE is the station code for Porto São Bento, a historic and centrally located railway station in Porto, Portugal.
E1011254 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: PSE | Statement: [Porto São Bento railway station, railwayStationCode, PSE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PSE
Context triple: [Porto São Bento railway station, railwayStationCode, PSE]
  • A. PSE
    PSE is a major European political party alliance that brings together socialist, social democratic, and labor parties from across the European Union.
  • B. PSE
    PSE is the IATA airport code for Mercedita Airport, a public airport serving the Ponce region in southern Puerto Rico.
  • C. PSE
    PSE is the national stock exchange of the Philippines, providing a marketplace for the trading of securities such as stocks and bonds.
  • D. PSB
    PSB is an acronym commonly used to refer to a Protective Services Bureau, a division typically responsible for safeguarding people, property, and critical assets.
  • E. PSB
    PSB is the division of the New York City Police Department responsible for overseeing and coordinating the city’s uniformed patrol operations across its precincts and boroughs.
  • 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: PSE
Triple: [Porto São Bento railway station, railwayStationCode, PSE]
Generated description
PSE is the station code for Porto São Bento, a historic and centrally located railway station in Porto, Portugal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PSE
Target entity description: PSE is the station code for Porto São Bento, a historic and centrally located railway station in Porto, Portugal.
  • A. PSE
    PSE is a major European political party alliance that brings together socialist, social democratic, and labor parties from across the European Union.
  • B. PSE
    PSE is the IATA airport code for Mercedita Airport, a public airport serving the Ponce region in southern Puerto Rico.
  • C. PSE
    PSE is the national stock exchange of the Philippines, providing a marketplace for the trading of securities such as stocks and bonds.
  • D. PSB
    PSB is Adobe Photoshop’s large document file format designed to handle images exceeding the size and layer limits of standard PSD files.
  • E. PSB
    PSB is an acronym commonly used to refer to a Protective Services Bureau, a division typically responsible for safeguarding people, property, and critical assets.
  • 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_69d7bdfb57a88190836b743e2825feca completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97e2b0108819098a681f93e90dbda completed April 10, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af7ba4d88190952622e7a07ab39e completed May 3, 2026, 2:14 a.m.
NEDg Description generation batch_69f6b066f3888190b925e5a43be57965 completed May 3, 2026, 2:18 a.m.
NED2 Entity disambiguation (via description) batch_69f6b1aa191081908266128776a2147a completed May 3, 2026, 2:23 a.m.
Created at: April 9, 2026, 5:44 p.m.