Triple

T3968791
Position Surface form Disambiguated ID Type / Status
Subject City and County of Swansea E92278 entity
Predicate contains P35 FINISHED
Object Landore
Landore is a district of Swansea in South Wales, known historically for its industrial heritage and proximity to the River Tawe.
E401996 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: Landore | Statement: [City and County of Swansea, contains, Landore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Landore
Context triple: [City and County of Swansea, contains, Landore]
  • A. Eythorne
    Eythorne is a small village in Kent, England, known for its rural character and location near the port town of Dover.
  • B. Ciergnon
    Ciergnon is a village in the Walloon region of Belgium known for its royal estate and the nearby Ciergnon Castle used by the Belgian royal family.
  • C. Henllys
    Henllys is a residential village and suburb forming part of the Cwmbran area in Torfaen, South Wales.
  • D. Streonshalh
    Streonshalh was the original Anglo-Saxon name for the monastic settlement that later became known as Whitby Abbey in Northumbria, England.
  • E. Rowardennan
    Rowardennan is a small village on the eastern shore of Loch Lomond in Scotland, known as a popular starting point for climbs up Ben Lomond.
  • 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: Landore
Triple: [City and County of Swansea, contains, Landore]
Generated description
Landore is a district of Swansea in South Wales, known historically for its industrial heritage and proximity to the River Tawe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Landore
Target entity description: Landore is a district of Swansea in South Wales, known historically for its industrial heritage and proximity to the River Tawe.
  • A. Eythorne
    Eythorne is a small village in Kent, England, known for its rural character and location near the port town of Dover.
  • B. Ciergnon
    Ciergnon is a village in the Walloon region of Belgium known for its royal estate and the nearby Ciergnon Castle used by the Belgian royal family.
  • C. Henllys
    Henllys is a residential village and suburb forming part of the Cwmbran area in Torfaen, South Wales.
  • D. Streonshalh
    Streonshalh was the original Anglo-Saxon name for the monastic settlement that later became known as Whitby Abbey in Northumbria, England.
  • E. Rowardennan
    Rowardennan is a small village on the eastern shore of Loch Lomond in Scotland, known as a popular starting point for climbs up Ben Lomond.
  • 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_69aed96624188190ac8c45bb57ab72b5 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef992d6bc8190be1b244eb87f2964 completed March 9, 2026, 4:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b533c39de881908916baaf8d8c6cd6 completed March 14, 2026, 10:09 a.m.
NEDg Description generation batch_69b5345c9f388190ae03a7baafd2b4a2 completed March 14, 2026, 10:11 a.m.
NED2 Entity disambiguation (via description) batch_69b534f4ca808190a02806f3b06c5b70 completed March 14, 2026, 10:14 a.m.
Created at: March 9, 2026, 3:32 p.m.