Triple

T15396653
Position Surface form Disambiguated ID Type / Status
Subject Theodore of Tarsus E368193 entity
Predicate predecessor P97 FINISHED
Object Wighard
Wighard was a 7th-century Anglo-Saxon cleric chosen to become Archbishop of Canterbury but who died in Rome before his consecration.
 E1154044 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: Wighard | Statement: [Theodore of Tarsus, predecessor, Wighard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wighard
Context triple: [Theodore of Tarsus, predecessor, Wighard]
  • A. Warnefrid
    Warnefrid was a Lombard nobleman of the 8th century best known as the father of the historian and monk Paul the Deacon.
  • B. Egbert
    Egbert is a small community in Wyoming, United States.
  • C. Egbert
    Egbert was a 9th-century king of Wessex who significantly expanded West Saxon power and laid foundations for the later unification of England.
  • D. Angilbert
    Angilbert was a Frankish nobleman, poet, and churchman who served as a close advisor to Charlemagne and later became abbot of the monastery of Saint-Riquier.
  • E. Thorismund
    Thorismund was a 5th-century king of the Visigoths, known for his role in the late Roman-era power struggles in Gaul.
  • 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: Wighard
Triple: [Theodore of Tarsus, predecessor, Wighard]
Generated description
Wighard was a 7th-century Anglo-Saxon cleric chosen to become Archbishop of Canterbury but who died in Rome before his consecration.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wighard
Target entity description: Wighard was a 7th-century Anglo-Saxon cleric chosen to become Archbishop of Canterbury but who died in Rome before his consecration.
  • A. Warnefrid
    Warnefrid was a Lombard nobleman of the 8th century best known as the father of the historian and monk Paul the Deacon.
  • B. Egbert
    Egbert is a small community in Wyoming, United States.
  • C. Egbert
    Egbert was a 9th-century king of Wessex who significantly expanded West Saxon power and laid foundations for the later unification of England.
  • D. Angilbert
    Angilbert was a Frankish nobleman, poet, and churchman who served as a close advisor to Charlemagne and later became abbot of the monastery of Saint-Riquier.
  • E. Thorismund
    Thorismund was a 5th-century king of the Visigoths, known for his role in the late Roman-era power struggles in Gaul.
  • 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_69d85a16c68c819099c1b547fbc87b32 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e8c5d40819086622b70edcb6294 completed April 16, 2026, 1:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff13542c908190abf765b0530c76ce completed May 9, 2026, 10:58 a.m.
NEDg Description generation batch_69ff14042ce8819084817836b096f175 completed May 9, 2026, 11:01 a.m.
NED2 Entity disambiguation (via description) batch_69ff14745a8c81909b10d6b21b88b50b completed May 9, 2026, 11:03 a.m.
Created at: April 10, 2026, 3:19 a.m.