Triple

T3400663
Position Surface form Disambiguated ID Type / Status
Subject Limerick E71642 entity
Predicate hasDistrict P459 FINISHED
Object Irishtown
Irishtown is a historic district in Limerick, Ireland, known as one of the city’s original medieval quarters.
E355948 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: Irishtown | Statement: [Limerick, hasDistrict, Irishtown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irishtown
Context triple: [Limerick, hasDistrict, Irishtown]
  • A. Irish Town
    Irish Town is a small settlement within the Parish of St. Andrew, known as a local community area in that region.
  • B. Threemiletown
    Threemiletown is a small village in West Lothian, Scotland, situated near the A89 road between Linlithgow and Bathgate.
  • C. Milltown
    Milltown is a small hamlet within the Town of Southeast in Putnam County, New York.
  • D. Finstown Hills
    Finstown Hills are a range of modest, windswept upland hills forming the highest terrain in the central part of Orkney’s Mainland in Scotland.
  • E. Bankstown
    Bankstown is a major multicultural suburb in south-western Sydney, Australia, known for its diverse community, commercial centre, and transport links.
  • 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: Irishtown
Triple: [Limerick, hasDistrict, Irishtown]
Generated description
Irishtown is a historic district in Limerick, Ireland, known as one of the city’s original medieval quarters.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Irishtown
Target entity description: Irishtown is a historic district in Limerick, Ireland, known as one of the city’s original medieval quarters.
  • A. Irish Town
    Irish Town is a small settlement within the Parish of St. Andrew, known as a local community area in that region.
  • B. Threemiletown
    Threemiletown is a small village in West Lothian, Scotland, situated near the A89 road between Linlithgow and Bathgate.
  • C. Milltown
    Milltown is a small hamlet within the Town of Southeast in Putnam County, New York.
  • D. Finstown Hills
    Finstown Hills are a range of modest, windswept upland hills forming the highest terrain in the central part of Orkney’s Mainland in Scotland.
  • E. Bankstown
    Bankstown is a major multicultural suburb in south-western Sydney, Australia, known for its diverse community, commercial centre, and transport links.
  • 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_69ad85aac4808190a092c9cc8911f584 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb8c80e0081909c3d5f95ab6f55a0 completed March 8, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bd01e108190995dcd3cb8ead793 completed March 12, 2026, 11:27 p.m.
NEDg Description generation batch_69b34e4792608190b74e02e065d4bc68 completed March 12, 2026, 11:37 p.m.
NED2 Entity disambiguation (via description) batch_69b3525f44948190af72b177193edca4 completed March 12, 2026, 11:55 p.m.
Created at: March 8, 2026, 3:14 p.m.