Triple

T8897759
Position Surface form Disambiguated ID Type / Status
Subject King Ban of Benwick E211847 entity
Predicate fatherOf P120 FINISHED
Object Lionel
Lionel is a knight of the Round Table in Arthurian legend, known as the son of King Ban of Benwick and the cousin of Sir Lancelot.
E766078 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: Lionel | Statement: [King Ban of Benwick, fatherOf, Lionel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lionel
Context triple: [King Ban of Benwick, fatherOf, Lionel]
  • A. Lionel
    Lionel is the given name of Lionel Logue, the Australian speech therapist renowned for helping King George VI overcome his stammer.
  • B. Lionel
    Lionel is the given name of Baron Walter Rothschild, a prominent British banker, politician, and zoologist from the famous Rothschild family.
  • C. Lionel
    Lionel is a masculine given name of Latin origin, commonly used in English- and French-speaking countries.
  • D. Leo the Lion
    Leo the Lion is the iconic roaring lion featured in the opening logo of Metro-Goldwyn-Mayer (MGM) films.
  • E. Leo the Lion
    Leo the Lion is the costumed lion mascot representing Purdue University Northwest’s athletic teams and school spirit.
  • 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: Lionel
Triple: [King Ban of Benwick, fatherOf, Lionel]
Generated description
Lionel is a knight of the Round Table in Arthurian legend, known as the son of King Ban of Benwick and the cousin of Sir Lancelot.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lionel
Target entity description: Lionel is a knight of the Round Table in Arthurian legend, known as the son of King Ban of Benwick and the cousin of Sir Lancelot.
  • A. Lionel
    Lionel is the given name of Lionel Logue, the Australian speech therapist renowned for helping King George VI overcome his stammer.
  • B. Lionel
    Lionel is the given name of Baron Walter Rothschild, a prominent British banker, politician, and zoologist from the famous Rothschild family.
  • C. Lionel
    Lionel is a masculine given name of Latin origin, commonly used in English- and French-speaking countries.
  • D. Leo the Lion
    Leo the Lion is the iconic roaring lion featured in the opening logo of Metro-Goldwyn-Mayer (MGM) films.
  • E. Leo the Lion
    Leo the Lion is the costumed lion mascot representing Purdue University Northwest’s athletic teams and school spirit.
  • 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_69ca83918d3081909b326fa3750cb8c8 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6424a8c08190aef2aa2079dd85f1 completed April 1, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba212fd081909ae87853c81e1d30 completed April 3, 2026, 1:01 p.m.
NEDg Description generation batch_69cfbab0b0048190a0ad002787dddffa completed April 3, 2026, 1:03 p.m.
NED2 Entity disambiguation (via description) batch_69cfbb4f1f6881908ec9e419d175d044 completed April 3, 2026, 1:06 p.m.
Created at: March 30, 2026, 6:54 p.m.