Triple

T18394731
Position Surface form Disambiguated ID Type / Status
Subject British Political Studies Association E449836 entity
Predicate abbreviation P43 FINISHED
Object PSA
PSA is the commonly used abbreviation for the British Political Studies Association, a professional organization for political science scholars in the United Kingdom.
 E1322183 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: PSA | Statement: [British Political Studies Association, abbreviation, PSA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PSA
Context triple: [British Political Studies Association, abbreviation, PSA]
  • A. PSA
    The PSA is a prominent literary organization known for supporting and honoring poets and poetry in the United States.
  • B. PSA
    The PSA is a landmark U.S. federal law enacted in 1921 to regulate fair competition and trade practices in the livestock, meatpacking, and poultry industries.
  • C. PSA
    PSA is the major port operator and logistics company that manages and develops Singapore’s world-leading container terminals.
  • D. PSA
    PSA is the three-letter IATA airport code for Pisa International Airport in Pisa, Italy.
  • E. PSA
    PSA is the ESA Planetary Science Archive, a central repository for data from the European Space Agency’s planetary missions.
  • 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: PSA
Triple: [British Political Studies Association, abbreviation, PSA]
Generated description
PSA is the commonly used abbreviation for the British Political Studies Association, a professional organization for political science scholars in the United Kingdom.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PSA
Target entity description: PSA is the commonly used abbreviation for the British Political Studies Association, a professional organization for political science scholars in the United Kingdom.
  • A. PSA
    The PSA is a landmark U.S. federal law enacted in 1921 to regulate fair competition and trade practices in the livestock, meatpacking, and poultry industries.
  • B. PSA
    PSA is the major port operator and logistics company that manages and develops Singapore’s world-leading container terminals.
  • C. PSA
    PSA is the three-letter IATA airport code for Pisa International Airport in Pisa, Italy.
  • D. PSA
    PSA is the ESA Planetary Science Archive, a central repository for data from the European Space Agency’s planetary missions.
  • E. PSA
    The PSA is a prominent literary organization known for supporting and honoring poets and poetry in the United States.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e51845d6708190bc96ec801e21b7a3 completed April 19, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03e240976c8190bcdeb3913cc32336 completed May 13, 2026, 2:30 a.m.
NEDg Description generation batch_6a03e2e51660819085ec36e697e94e6a completed May 13, 2026, 2:33 a.m.
NED2 Entity disambiguation (via description) batch_6a03e39ae800819082963203b07d9042 completed May 13, 2026, 2:36 a.m.
Created at: April 10, 2026, 10:46 a.m.