Triple

T5100353
Position Surface form Disambiguated ID Type / Status
Subject County Tyrone E114966 entity
Predicate hasSettlement P1068 FINISHED
Object Stewartstown
Stewartstown is a small village in County Tyrone, Northern Ireland, known for its rural character and historic market-town origins.
E495251 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: Stewartstown | Statement: [County Tyrone, hasSettlement, Stewartstown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stewartstown
Context triple: [County Tyrone, hasSettlement, Stewartstown]
  • A. Stewarttown
    Stewarttown is a small community located within the town of Halton Hills in Ontario, Canada.
  • B. Rochestown
    Rochestown is a suburban residential area on the southeastern outskirts of Cork city in Ireland, known for its proximity to the River Lee and good transport links into the city.
  • C. Tylorstown
    Tylorstown is a former coal mining village in the Rhondda Fach valley in Rhondda Cynon Taf, Wales.
  • D. Shingletown
    Shingletown is a small rural community in Northern California known for its forested setting near Lassen Volcanic National Park.
  • E. Diggstown
    Diggstown is a 1992 sports comedy-drama film centered on a high-stakes boxing con set in a small Southern town.
  • 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: Stewartstown
Triple: [County Tyrone, hasSettlement, Stewartstown]
Generated description
Stewartstown is a small village in County Tyrone, Northern Ireland, known for its rural character and historic market-town origins.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Stewartstown
Target entity description: Stewartstown is a small village in County Tyrone, Northern Ireland, known for its rural character and historic market-town origins.
  • A. Stewarttown
    Stewarttown is a small community located within the town of Halton Hills in Ontario, Canada.
  • B. Rochestown
    Rochestown is a suburban residential area on the southeastern outskirts of Cork city in Ireland, known for its proximity to the River Lee and good transport links into the city.
  • C. Tylorstown
    Tylorstown is a former coal mining village in the Rhondda Fach valley in Rhondda Cynon Taf, Wales.
  • D. Shingletown
    Shingletown is a small rural community in Northern California known for its forested setting near Lassen Volcanic National Park.
  • E. Diggstown
    Diggstown is a 1992 sports comedy-drama film centered on a high-stakes boxing con set in a small Southern town.
  • 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_69bd443fc49c819089629c00e311310c completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd758381dc8190ac491788d27ab8e0 completed March 20, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec36d231481908da4d2df53bd6507 completed March 21, 2026, 4:12 p.m.
NEDg Description generation batch_69bec506d5b88190bcf6e7cb5f602c2f completed March 21, 2026, 4:19 p.m.
NED2 Entity disambiguation (via description) batch_69bec5ae111c8190914e93dc1680d36e completed March 21, 2026, 4:22 p.m.
Created at: March 20, 2026, 1:40 p.m.