Triple

T903762
Position Surface form Disambiguated ID Type / Status
Subject Lisbon Tramway E19501 entity
Predicate servesArea P82 FINISHED
Object Estrela
Estrela is a historic and picturesque neighborhood in Lisbon, Portugal, known for its basilica, gardens, and traditional tram routes.
E106470 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: Estrela | Statement: [Lisbon Tramway, servesArea, Estrela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Estrela
Context triple: [Lisbon Tramway, servesArea, Estrela]
  • A. Étoile
    Étoile was the former name of the Paris Métro station now known as Charles de Gaulle–Étoile, located near the Arc de Triomphe at Place Charles de Gaulle.
  • B. Stella Maris
    Stella Maris is a traditional Latin title for the Virgin Mary, often invoked by seafarers and associated with guidance and protection.
  • C. Jandali
    Jandali is an Arabic family name most notably associated with Abdulfattah Jandali, the biological father of Apple co-founder Steve Jobs.
  • D. Meliae
    The Meliae are nymphs from Greek mythology associated with ash trees and often linked to the early generations of humanity and rustic woodland life.
  • E. Loralai
    Loralai is a town and district in northern Balochistan, Pakistan, known historically as a regional administrative and trade center.
  • 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: Estrela
Triple: [Lisbon Tramway, servesArea, Estrela]
Generated description
Estrela is a historic and picturesque neighborhood in Lisbon, Portugal, known for its basilica, gardens, and traditional tram routes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Estrela
Target entity description: Estrela is a historic and picturesque neighborhood in Lisbon, Portugal, known for its basilica, gardens, and traditional tram routes.
  • A. Étoile
    Étoile was the former name of the Paris Métro station now known as Charles de Gaulle–Étoile, located near the Arc de Triomphe at Place Charles de Gaulle.
  • B. Stella Maris
    Stella Maris is a traditional Latin title for the Virgin Mary, often invoked by seafarers and associated with guidance and protection.
  • C. Jandali
    Jandali is an Arabic family name most notably associated with Abdulfattah Jandali, the biological father of Apple co-founder Steve Jobs.
  • D. Meliae
    The Meliae are nymphs from Greek mythology associated with ash trees and often linked to the early generations of humanity and rustic woodland life.
  • E. Logudoro
    Logudoro is a historical-cultural region in northern Sardinia known for its distinctive Sardinian dialect, medieval heritage, and rural landscapes.
  • 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_69a4939e889c8190ac148b3ac1a7f90b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ad58334881908df191140b786780 completed March 1, 2026, 9:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c736bb6c8190a9cad1ef536be785 completed March 4, 2026, 5:46 a.m.
NEDg Description generation batch_69a7c7a5f03c81908bd3ed9eb3710141 completed March 4, 2026, 5:48 a.m.
NED2 Entity disambiguation (via description) batch_69a7c888cd98819082dc39739d14dc67 completed March 4, 2026, 5:52 a.m.
Created at: March 1, 2026, 7:39 p.m.