Triple

T18990900
Position Surface form Disambiguated ID Type / Status
Subject Ernesto Cardenal E464678 entity
Predicate notableWork P4 FINISHED
Object Epigramas
Epigramas is a celebrated collection of politically charged and romantically themed poems by Nicaraguan poet and priest Ernesto Cardenal.
 E1353648 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: Epigramas | Statement: [Ernesto Cardenal, notableWork, Epigramas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Epigramas
Context triple: [Ernesto Cardenal, notableWork, Epigramas]
  • A. Epigrams
    Epigrams is a collection of short, witty, and often pointed poetic compositions attributed to the Hellenistic Greek poet Callimachus.
  • B. Epigrams
    Epigrams is a collection of short, witty, and often satirical poems by the French Renaissance poet Clément Marot.
  • C. Epigram
    Epigram is a dependently typed functional programming language and proof assistant that explored interactive program development and influenced later languages like Idris.
  • D. Epitadas
    Epitadas was a Spartan commander best known for leading the Spartan garrison on the island of Sphacteria during the Peloponnesian War.
  • E. Aphorisms
    Aphorisms is a seminal medical text by Hippocrates consisting of concise statements that summarize clinical observations and principles of ancient Greek medicine.
  • 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: Epigramas
Triple: [Ernesto Cardenal, notableWork, Epigramas]
Generated description
Epigramas is a celebrated collection of politically charged and romantically themed poems by Nicaraguan poet and priest Ernesto Cardenal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Epigramas
Target entity description: Epigramas is a celebrated collection of politically charged and romantically themed poems by Nicaraguan poet and priest Ernesto Cardenal.
  • A. Epigrams
    Epigrams is a collection of short, witty, and often pointed poetic compositions attributed to the Hellenistic Greek poet Callimachus.
  • B. Epigrams
    Epigrams is a collection of short, witty, and often satirical poems by the French Renaissance poet Clément Marot.
  • C. Epigram
    Epigram is a dependently typed functional programming language and proof assistant that explored interactive program development and influenced later languages like Idris.
  • D. Epitadas
    Epitadas was a Spartan commander best known for leading the Spartan garrison on the island of Sphacteria during the Peloponnesian War.
  • E. Aphorisms
    Aphorisms is a seminal medical text by Hippocrates consisting of concise statements that summarize clinical observations and principles of ancient Greek medicine.
  • 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d67dee4c8190ac2017ff748ea6aa completed April 20, 2026, 7:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05b45340888190a21cea6e72b7facc completed May 14, 2026, 11:38 a.m.
NEDg Description generation batch_6a05b62d8aec81908b71232f52eb3612 completed May 14, 2026, 11:46 a.m.
NED2 Entity disambiguation (via description) batch_6a05b68aba3081908ca21d732e45f454 completed May 14, 2026, 11:48 a.m.
Created at: April 10, 2026, 12:01 p.m.