Triple

T12469548
Position Surface form Disambiguated ID Type / Status
Subject British–Irish Parliamentary Assembly E298016 entity
Predicate shortName P43 FINISHED
Object BIPA
BIPA is the commonly used acronym for the British–Irish Parliamentary Assembly, a forum for parliamentary cooperation between the UK, Ireland, and the British–Irish Council jurisdictions.
E983762 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: BIPA | Statement: [British–Irish Parliamentary Assembly, shortName, BIPA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BIPA
Context triple: [British–Irish Parliamentary Assembly, shortName, BIPA]
  • A. BIA
    BIA is the acronym for the Board of Immigration Appeals, the highest administrative body for interpreting and applying U.S. immigration laws.
  • B. BIA
    BIA is a U.S. federal agency within the Department of the Interior responsible for managing relations and services for Native American tribes and Alaska Natives.
  • C. BIA
    BIA is the IATA airport code for Bastia – Poretta Airport, the main air gateway serving the city of Bastia on the French island of Corsica.
  • D. BIA
    BIA is the station code used to identify Białystok railway station in Poland’s rail network.
  • E. BIA
    BIA is a contributor associated with the Safari web browser project.
  • 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: BIPA
Triple: [British–Irish Parliamentary Assembly, shortName, BIPA]
Generated description
BIPA is the commonly used acronym for the British–Irish Parliamentary Assembly, a forum for parliamentary cooperation between the UK, Ireland, and the British–Irish Council jurisdictions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BIPA
Target entity description: BIPA is the commonly used acronym for the British–Irish Parliamentary Assembly, a forum for parliamentary cooperation between the UK, Ireland, and the British–Irish Council jurisdictions.
  • A. BIA
    BIA is the acronym for the Board of Immigration Appeals, the highest administrative body for interpreting and applying U.S. immigration laws.
  • B. BIA
    BIA is a U.S. federal agency within the Department of the Interior responsible for managing relations and services for Native American tribes and Alaska Natives.
  • C. BIA
    BIA is the IATA airport code for Bastia – Poretta Airport, the main air gateway serving the city of Bastia on the French island of Corsica.
  • D. BIA
    BIA is the station code used to identify Białystok railway station in Poland’s rail network.
  • E. BIA
    BIA is a contributor associated with the Safari web browser project.
  • 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_69d6ada270808190b1a2b2e7b02bb426 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94dba7f6c8190b272f649e0777362 completed April 10, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f2175c48190bbd28ad8c07434f0 completed May 2, 2026, 6:14 p.m.
NEDg Description generation batch_69f6401199408190ad2657802afd93c9 completed May 2, 2026, 6:18 p.m.
NED2 Entity disambiguation (via description) batch_69f64168d23881908daee7d7cba2160d completed May 2, 2026, 6:24 p.m.
Created at: April 8, 2026, 9:56 p.m.