Triple

T18680135
Position Surface form Disambiguated ID Type / Status
Subject Wear Valley E456710 entity
Predicate containsSettlement P847 FINISHED
Object Coundon
Coundon is a village in County Durham, England, historically associated with coal mining and situated near the town of Bishop Auckland.
E1337320 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: Coundon | Statement: [Wear Valley, containsSettlement, Coundon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coundon
Context triple: [Wear Valley, containsSettlement, Coundon]
  • A. Gourdon
    Gourdon is a historic hilltop town in southern France known for its medieval architecture and panoramic views over the surrounding countryside.
  • B. Gourdon
    Gourdon is a small coastal fishing village in eastern Scotland known for its historic harbour and North Sea views.
  • C. Aigremont
    Aigremont is a small French commune located in the Yvelines department in north-central France.
  • D. Coryton
    Coryton is a suburban area and railway terminus in Cardiff, Wales, served by local commuter trains.
  • E. Seynod
    Seynod is a former commune in southeastern France, now merged into the city of Annecy in the Haute-Savoie department of the Auvergne-Rhône-Alpes region.
  • 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: Coundon
Triple: [Wear Valley, containsSettlement, Coundon]
Generated description
Coundon is a village in County Durham, England, historically associated with coal mining and situated near the town of Bishop Auckland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Coundon
Target entity description: Coundon is a village in County Durham, England, historically associated with coal mining and situated near the town of Bishop Auckland.
  • A. Gourdon
    Gourdon is a historic hilltop town in southern France known for its medieval architecture and panoramic views over the surrounding countryside.
  • B. Gourdon
    Gourdon is a small coastal fishing village in eastern Scotland known for its historic harbour and North Sea views.
  • C. Aigremont
    Aigremont is a small French commune located in the Yvelines department in north-central France.
  • D. Coryton
    Coryton is a suburban area and railway terminus in Cardiff, Wales, served by local commuter trains.
  • E. Seynod
    Seynod is a former commune in southeastern France, now merged into the city of Annecy in the Haute-Savoie department of the Auvergne-Rhône-Alpes region.
  • 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_69d8d391eb488190ac2e9abf5bf255e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e55b2783648190bb602e2b07eedf92 completed April 19, 2026, 10:45 p.m.
NED1 Entity disambiguation (via context triple) batch_6a052355d4ec819099c19ff2662df92f completed May 14, 2026, 1:20 a.m.
NEDg Description generation batch_6a05247c52f08190b8c9cf9268f65a82 completed May 14, 2026, 1:25 a.m.
NED2 Entity disambiguation (via description) batch_6a0524eced608190a1b3468f6d0189c2 completed May 14, 2026, 1:27 a.m.
Created at: April 10, 2026, 11:48 a.m.