Triple

T11025200
Position Surface form Disambiguated ID Type / Status
Subject Northside Dublin E260599 entity
Predicate hasNeighbourhood P4813 FINISHED
Object Artane
Artane is a residential suburb on Dublin’s Northside, known for its local shopping centre, schools, and proximity to the city centre.
E900513 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: Artane | Statement: [Northside Dublin, hasNeighbourhood, Artane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Artane
Context triple: [Northside Dublin, hasNeighbourhood, Artane]
  • A. pimozide
    Pimozide is a typical antipsychotic medication primarily used to treat Tourette’s disorder and severe tics.
  • B. thioridazine
    Thioridazine is an older antipsychotic medication from the phenothiazine class, primarily used in the past to treat schizophrenia but now rarely prescribed due to its risk of serious heart rhythm disturbances.
  • C. Acurenam
    Acurenam is a town located in the Centro Sur province of Equatorial Guinea.
  • D. levodopa
    Levodopa is a cornerstone medication for managing Parkinson’s disease symptoms by replenishing the brain’s depleted dopamine levels.
  • E. carbidopa
    Carbidopa is a medication used in combination with levodopa to treat Parkinson’s disease by preventing peripheral breakdown of levodopa and reducing its side effects.
  • 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: Artane
Triple: [Northside Dublin, hasNeighbourhood, Artane]
Generated description
Artane is a residential suburb on Dublin’s Northside, known for its local shopping centre, schools, and proximity to the city centre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Artane
Target entity description: Artane is a residential suburb on Dublin’s Northside, known for its local shopping centre, schools, and proximity to the city centre.
  • A. pimozide
    Pimozide is a typical antipsychotic medication primarily used to treat Tourette’s disorder and severe tics.
  • B. thioridazine
    Thioridazine is an older antipsychotic medication from the phenothiazine class, primarily used in the past to treat schizophrenia but now rarely prescribed due to its risk of serious heart rhythm disturbances.
  • C. Acurenam
    Acurenam is a town located in the Centro Sur province of Equatorial Guinea.
  • D. levodopa
    Levodopa is a cornerstone medication for managing Parkinson’s disease symptoms by replenishing the brain’s depleted dopamine levels.
  • E. carbidopa
    Carbidopa is a medication used in combination with levodopa to treat Parkinson’s disease by preventing peripheral breakdown of levodopa and reducing its side effects.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797bf78a48190a37b423812827d4e completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e37523f8548190ad40fa76660232a8 completed April 18, 2026, 12:12 p.m.
NEDg Description generation batch_69e37ab860f48190808ba0076cfa9c98 completed April 18, 2026, 12:36 p.m.
NED2 Entity disambiguation (via description) batch_69e3864dd0d48190b3fd81381f5d7418 completed April 18, 2026, 1:25 p.m.
Created at: April 8, 2026, 9:25 p.m.