Triple

T12784688
Position Surface form Disambiguated ID Type / Status
Subject Centre for European Legal Studies E305593 entity
Predicate abbreviation P43 FINISHED
Object CELS
CELS is a research and teaching centre focused on European law and legal integration, typically associated with a university law faculty.
E1002366 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: CELS | Statement: [Centre for European Legal Studies, abbreviation, CELS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CELS
Context triple: [Centre for European Legal Studies, abbreviation, CELS]
  • A. CELC
    CELC is an international association of conservative Lutheran church bodies that share a common confessional stance based on the Lutheran Confessions.
  • B. Cel
    Cel is an Etruscan goddess associated with the earth and the underworld in ancient Italic religion.
  • C. CELARG
    CELARG is a Venezuelan cultural and research institution dedicated to promoting Latin American literature, thought, and the legacy of writer Rómulo Gallegos.
  • D. Cellese
    Cellese is a regional dialect of the Franco-Provençal language traditionally spoken in a specific area of the Franco-Provençal linguistic region.
  • E. Celle line
    The Celle line was a cadet branch of the House of Brunswick-Lüneburg that ruled the Principality of Lüneburg from the town of Celle in early modern Germany.
  • 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: CELS
Triple: [Centre for European Legal Studies, abbreviation, CELS]
Generated description
CELS is a research and teaching centre focused on European law and legal integration, typically associated with a university law faculty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CELS
Target entity description: CELS is a research and teaching centre focused on European law and legal integration, typically associated with a university law faculty.
  • A. CELC
    CELC is an international association of conservative Lutheran church bodies that share a common confessional stance based on the Lutheran Confessions.
  • B. Cel
    Cel is an Etruscan goddess associated with the earth and the underworld in ancient Italic religion.
  • C. CELARG
    CELARG is a Venezuelan cultural and research institution dedicated to promoting Latin American literature, thought, and the legacy of writer Rómulo Gallegos.
  • D. Cellese
    Cellese is a regional dialect of the Franco-Provençal language traditionally spoken in a specific area of the Franco-Provençal linguistic region.
  • E. Celle line
    The Celle line was a cadet branch of the House of Brunswick-Lüneburg that ruled the Principality of Lüneburg from the town of Celle in early modern Germany.
  • 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_69d7bdf2b43c819098ae5aa68e61ea58 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e5cb3c08190b8e1e22de8b96e17 completed April 10, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68504c95081909dc52cc02e43e8ba completed May 2, 2026, 11:13 p.m.
NEDg Description generation batch_69f687fffe9c81909c58129162a0c231 completed May 2, 2026, 11:25 p.m.
NED2 Entity disambiguation (via description) batch_69f688cc57048190ba7bacdcd6c0c182 completed May 2, 2026, 11:29 p.m.
Created at: April 9, 2026, 5:29 p.m.