Triple

T19322701
Position Surface form Disambiguated ID Type / Status
Subject Kurwenal E483265 entity
Predicate defends P6876 FINISHED
Object Tristan NE NERFINISHED

How this triple was built (2 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: Tristan | Statement: [Kurwenal, defends, Tristan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tristan
Context triple: [Kurwenal, defends, Tristan]
  • A. Tristan chosen
    "Tristan" is a seminal Middle High German courtly romance, most famously adapted by Gottfried von Strassburg, that recounts the tragic love story of the knight Tristan and the Irish princess Isolde.
  • B. Tristan
    Tristan is a skilled and stoic Sarmatian knight in the 2004 film "King Arthur," known for his deadly archery and falconry.
  • C. Tristan bunting
    Tristan bunting is a small passerine bird species endemic to the Tristan da Cunha island group in the South Atlantic Ocean.
  • D. Tristán
    Tristán is the given name of Tristán de Luna y Arellano, a 16th-century Spanish conquistador and explorer involved in early attempts to colonize what is now the southeastern United States.
  • E. Tristram of Blent
    Tristram of Blent is a lesser-known 1901 romantic novel by British author Anthony Hope, blending social comedy with themes of inheritance and identity in an English country-house setting.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8d13e3c81909d91d1d5ec37c095 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e60d8948948190b76a384041333509 completed April 20, 2026, 11:27 a.m.
Created at: April 10, 2026, 1:32 p.m.