Triple

T14113599
Position Surface form Disambiguated ID Type / Status
Subject Leiden University Centre for Linguistics E339705 entity
Predicate abbreviation P43 FINISHED
Object LUCL
LUCL is a research and teaching institute at Leiden University specializing in linguistics and language-related studies.
E1079615 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: LUCL | Statement: [Leiden University Centre for Linguistics, abbreviation, LUCL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LUCL
Context triple: [Leiden University Centre for Linguistics, abbreviation, LUCL]
  • A. LCL
    LCL is a visual component framework used by the Lazarus IDE to build cross-platform graphical user interfaces in Free Pascal.
  • B. LCL
    LCL is the standard abbreviation for the Loeb Classical Library, a renowned series of books presenting classical Greek and Latin texts with facing-page English translations.
  • C. ULCA
    ULCA was a major Lutheran denomination in the United States that existed from 1918 until it merged into the Lutheran Church in America in 1962.
  • D. LRCL
    LRCL is the ICAO airport code for Cluj International Airport in Cluj-Napoca, Romania.
  • E. UCLS
    UCLS is a renowned private day school in Chicago affiliated with the University of Chicago, known for its progressive education and strong academic programs from nursery through high school.
  • 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: LUCL
Triple: [Leiden University Centre for Linguistics, abbreviation, LUCL]
Generated description
LUCL is a research and teaching institute at Leiden University specializing in linguistics and language-related studies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LUCL
Target entity description: LUCL is a research and teaching institute at Leiden University specializing in linguistics and language-related studies.
  • A. LCL
    LCL is a visual component framework used by the Lazarus IDE to build cross-platform graphical user interfaces in Free Pascal.
  • B. LCL
    LCL is the standard abbreviation for the Loeb Classical Library, a renowned series of books presenting classical Greek and Latin texts with facing-page English translations.
  • C. ULCA
    ULCA was a major Lutheran denomination in the United States that existed from 1918 until it merged into the Lutheran Church in America in 1962.
  • D. LRCL
    LRCL is the ICAO airport code for Cluj International Airport in Cluj-Napoca, Romania.
  • E. UCLS
    UCLS is a renowned private day school in Chicago affiliated with the University of Chicago, known for its progressive education and strong academic programs from nursery through high school.
  • 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de600f992c81908133813f2894dcca completed April 14, 2026, 3:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0b881388190a5bcdd87fd10c516 completed May 7, 2026, 5:49 p.m.
NEDg Description generation batch_69fcd2d99c4c8190baf15d470ead7b1c completed May 7, 2026, 5:58 p.m.
NED2 Entity disambiguation (via description) batch_69fcd3853e848190a210d1c8c08bd6cc completed May 7, 2026, 6:01 p.m.
Created at: April 9, 2026, 10:22 p.m.