Triple

T176321
Position Surface form Disambiguated ID Type / Status
Subject Portuguese language E3583 entity
Predicate regulatedBy P86 FINISHED
Object Academia das Ciências de Lisboa
Academia das Ciências de Lisboa is Portugal’s national academy of sciences, a scholarly institution that plays a central role in promoting scientific research and overseeing linguistic and cultural standards.
E22087 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: Academia das Ciências de Lisboa | Statement: [Portuguese language, regulatedBy, Academia das Ciências de Lisboa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Academia das Ciências de Lisboa
Context triple: [Portuguese language, regulatedBy, Academia das Ciências de Lisboa]
  • A. University of Lisbon
    The University of Lisbon is Portugal’s largest and one of its oldest public universities, renowned for its broad range of academic programs and major role in the country’s research and cultural life.
  • B. ISCTE – University Institute of Lisbon
    ISCTE – University Institute of Lisbon is a Portuguese public university-level institution in Lisbon known for its strong programs in social sciences, management, technology, and architecture.
  • C. NOVA University Lisbon
    NOVA University Lisbon is a leading Portuguese public research university known for its innovative teaching, strong international orientation, and multidisciplinary programs across fields such as science, technology, social sciences, and humanities.
  • D. Coimbra Group
    The Coimbra Group is an association of long-established, high-ranking European universities dedicated to academic collaboration, research excellence, and cultural exchange.
  • E. Academy of Sciences for the Developing World
    The Academy of Sciences for the Developing World, now known as The World Academy of Sciences (TWAS), is an international organization that supports scientific excellence and capacity building in developing countries.
  • 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: Academia das Ciências de Lisboa
Triple: [Portuguese language, regulatedBy, Academia das Ciências de Lisboa]
Generated description
Academia das Ciências de Lisboa is Portugal’s national academy of sciences, a scholarly institution that plays a central role in promoting scientific research and overseeing linguistic and cultural standards.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Academia das Ciências de Lisboa
Target entity description: Academia das Ciências de Lisboa is Portugal’s national academy of sciences, a scholarly institution that plays a central role in promoting scientific research and overseeing linguistic and cultural standards.
  • A. University of Lisbon
    The University of Lisbon is Portugal’s largest and one of its oldest public universities, renowned for its broad range of academic programs and major role in the country’s research and cultural life.
  • B. ISCTE – University Institute of Lisbon
    ISCTE – University Institute of Lisbon is a Portuguese public university-level institution in Lisbon known for its strong programs in social sciences, management, technology, and architecture.
  • C. NOVA University Lisbon
    NOVA University Lisbon is a leading Portuguese public research university known for its innovative teaching, strong international orientation, and multidisciplinary programs across fields such as science, technology, social sciences, and humanities.
  • D. Coimbra Group
    The Coimbra Group is an association of long-established, high-ranking European universities dedicated to academic collaboration, research excellence, and cultural exchange.
  • E. Academy of Sciences for the Developing World
    The Academy of Sciences for the Developing World, now known as The World Academy of Sciences (TWAS), is an international organization that supports scientific excellence and capacity building in developing countries.
  • 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_69a25374990081909766d30c79a18e0e completed Feb. 28, 2026, 2:31 a.m.
NER Named-entity recognition batch_69a258e497788190aeb61d981efb4d1d completed Feb. 28, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2eb7babec8190a1c1a6bcc94605ef completed Feb. 28, 2026, 1:19 p.m.
NEDg Description generation batch_69a2ec72092c8190bcc1efa7c0644560 completed Feb. 28, 2026, 1:24 p.m.
NED2 Entity disambiguation (via description) batch_69a2ecba99cc8190a85dd5e9c531a6e3 completed Feb. 28, 2026, 1:25 p.m.
Created at: Feb. 28, 2026, 2:39 a.m.