Triple

T13891643
Position Surface form Disambiguated ID Type / Status
Subject Intercidades E333984 entity
Predicate route P5619 FINISHED
Object Lisbon–Beja
Lisbon–Beja is a long-distance Intercidades rail service in Portugal connecting the capital city Lisbon with the inland city of Beja.
 E1076985 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: Lisbon–Beja | Statement: [Intercidades, route, Lisbon–Beja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lisbon–Beja
Context triple: [Intercidades, route, Lisbon–Beja]
  • A. Lisbon–Covilhã
    Lisbon–Covilhã is a long-distance Intercidades rail service in Portugal connecting the capital city Lisbon with the inland city of Covilhã across the country’s central region.
  • B. Lisbon–Guarda
    Lisbon–Guarda is a long-distance Intercidades rail service in Portugal connecting the capital city Lisbon with the inland city of Guarda.
  • C. Lisbon–Évora
    Lisbon–Évora is a mainline railway route in Portugal connecting the capital city Lisbon with the historic city of Évora.
  • D. Porto–Faro
    Porto–Faro is a major long-distance rail route in Portugal linking the northern city of Porto with the southern Algarve city of Faro.
  • E. Lisbon–Guimarães
    Lisbon–Guimarães is a major intercity rail route in Portugal connecting the capital Lisbon with the historic northern city of Guimarães.
  • 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: Lisbon–Beja
Triple: [Intercidades, route, Lisbon–Beja]
Generated description
Lisbon–Beja is a long-distance Intercidades rail service in Portugal connecting the capital city Lisbon with the inland city of Beja.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lisbon–Beja
Target entity description: Lisbon–Beja is a long-distance Intercidades rail service in Portugal connecting the capital city Lisbon with the inland city of Beja.
  • A. Lisbon–Covilhã
    Lisbon–Covilhã is a long-distance Intercidades rail service in Portugal connecting the capital city Lisbon with the inland city of Covilhã across the country’s central region.
  • B. Lisbon–Guarda
    Lisbon–Guarda is a long-distance Intercidades rail service in Portugal connecting the capital city Lisbon with the inland city of Guarda.
  • C. Lisbon–Évora
    Lisbon–Évora is a mainline railway route in Portugal connecting the capital city Lisbon with the historic city of Évora.
  • D. Porto–Faro
    Porto–Faro is a major long-distance rail route in Portugal linking the northern city of Porto with the southern Algarve city of Faro.
  • E. Lisbon–Guimarães
    Lisbon–Guimarães is a major intercity rail route in Portugal connecting the capital Lisbon with the historic northern city of Guimarães.
  • 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_69d81c5dd2d48190b7a5fc1e009de936 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de23a537d4819093c2bae2a244816a completed April 14, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69fbc31c38e481909a86cda6c913fb8e completed May 6, 2026, 10:39 p.m.
NEDg Description generation batch_69fc7e2e49508190a6a3211c9008d053 completed May 7, 2026, 11:57 a.m.
NED2 Entity disambiguation (via description) batch_69fc7f56979c8190a549079a4ea5d516 completed May 7, 2026, 12:02 p.m.
Created at: April 9, 2026, 10:15 p.m.