Triple

T12610274
Position Surface form Disambiguated ID Type / Status
Subject Conn E301095 entity
Predicate hasVariant P455 FINISHED
Object Conán
Conán is an Irish given name, historically borne by figures in Gaelic legend and tradition and related to the name Conn.
 E995898 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: Conán | Statement: [Conn, hasVariant, Conán]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Conán
Context triple: [Conn, hasVariant, Conán]
  • A. Conan
    Conan is an Irish-American television host, comedian, writer, and producer best known for hosting late-night talk shows such as "Late Night with Conan O'Brien" and "Conan."
  • B. Conan the Barbarian
    Conan the Barbarian is a 1982 fantasy adventure film that helped launch Arnold Schwarzenegger to stardom through his portrayal of the iconic sword-and-sorcery hero.
  • C. Conon
    Conon was a prominent 5th–4th century BCE Athenian admiral best known for rebuilding Athens’ naval power after its defeat in the Peloponnesian War.
  • D. Durkan
    Durkan is a surname most notably associated with Jenny Durkan, the former mayor of Seattle and an American attorney and politician.
  • E. Tamraght
    Tamraght is a small coastal village in southern Morocco known for its surf-friendly beaches and relaxed atmosphere near Agadir.
  • 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: Conán
Triple: [Conn, hasVariant, Conán]
Generated description
Conán is an Irish given name, historically borne by figures in Gaelic legend and tradition and related to the name Conn.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Conán
Target entity description: Conán is an Irish given name, historically borne by figures in Gaelic legend and tradition and related to the name Conn.
  • A. Conan
    Conan is an Irish-American television host, comedian, writer, and producer best known for hosting late-night talk shows such as "Late Night with Conan O'Brien" and "Conan."
  • B. Conan the Barbarian
    Conan the Barbarian is a 1982 fantasy adventure film that helped launch Arnold Schwarzenegger to stardom through his portrayal of the iconic sword-and-sorcery hero.
  • C. Conon
    Conon was a prominent 5th–4th century BCE Athenian admiral best known for rebuilding Athens’ naval power after its defeat in the Peloponnesian War.
  • D. Durkan
    Durkan is a surname most notably associated with Jenny Durkan, the former mayor of Seattle and an American attorney and politician.
  • E. Tamraght
    Tamraght is a small coastal village in southern Morocco known for its surf-friendly beaches and relaxed atmosphere near Agadir.
  • 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_69d7bdea2ca881908f379526c13b1145 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954ea1d748190a848e8a7873e2ea5 completed April 10, 2026, 7:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6686b9d088190832d1f244e7aa924 completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f66a602f088190984fa3381b5be944 completed May 2, 2026, 9:19 p.m.
NED2 Entity disambiguation (via description) batch_69f66b18e68881908bf79ab52bcc909e completed May 2, 2026, 9:22 p.m.
Created at: April 9, 2026, 5:11 p.m.