Triple

T3962429
Position Surface form Disambiguated ID Type / Status
Subject Middle Saxons E85935 entity
Predicate capital P234 FINISHED
Object Lundenwic
Lundenwic was the early medieval trading settlement and urban center of the Middle Saxons that preceded the later walled city of London.
 E401572 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: Lundenwic | Statement: [Middle Saxons, capital, Lundenwic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lundenwic
Context triple: [Middle Saxons, capital, Lundenwic]
  • A. Wicken
    Wicken is a small rural village in East Cambridgeshire, England, best known for its proximity to the National Trust’s Wicken Fen nature reserve, one of the country’s oldest wetlands.
  • B. Southwold
    Southwold is a residential neighbourhood within the town of Bicester in Oxfordshire, England.
  • C. Southwold
    Southwold is a small seaside town and popular tourist resort on the North Sea coast of Suffolk, England, known for its pier, beach huts, and historic lighthouse.
  • D. Jórvík
    Jórvík is the Old Norse name for the city of York during its period as a major Viking settlement and trading center in early medieval England.
  • E. Corvey
    Corvey is a historic former Benedictine abbey complex on the Weser River in Höxter, Germany, renowned for its Carolingian architecture and cultural significance.
  • 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: Lundenwic
Triple: [Middle Saxons, capital, Lundenwic]
Generated description
Lundenwic was the early medieval trading settlement and urban center of the Middle Saxons that preceded the later walled city of London.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lundenwic
Target entity description: Lundenwic was the early medieval trading settlement and urban center of the Middle Saxons that preceded the later walled city of London.
  • A. Wicken
    Wicken is a small rural village in East Cambridgeshire, England, best known for its proximity to the National Trust’s Wicken Fen nature reserve, one of the country’s oldest wetlands.
  • B. Southwold
    Southwold is a residential neighbourhood within the town of Bicester in Oxfordshire, England.
  • C. Southwold
    Southwold is a small seaside town and popular tourist resort on the North Sea coast of Suffolk, England, known for its pier, beach huts, and historic lighthouse.
  • D. Jórvík
    Jórvík is the Old Norse name for the city of York during its period as a major Viking settlement and trading center in early medieval England.
  • E. Corvey
    Corvey is a historic former Benedictine abbey complex on the Weser River in Höxter, Germany, renowned for its Carolingian architecture and cultural significance.
  • 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_69aed93a96908190bcbdbfa718f155bd completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef971e5608190a66361484a6f52dc completed March 9, 2026, 4:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b533b8e00c819093af24f27eee793b completed March 14, 2026, 10:08 a.m.
NEDg Description generation batch_69b5346fb3648190b2b72e10179588ed completed March 14, 2026, 10:11 a.m.
NED2 Entity disambiguation (via description) batch_69b534e98b8081909c2b71ff20fe0bb4 completed March 14, 2026, 10:14 a.m.
Created at: March 9, 2026, 3:31 p.m.