Triple

T6030708
Position Surface form Disambiguated ID Type / Status
Subject A Prayer Book for Australia E134293 entity
Predicate hasAlternativeTitle P39 FINISHED
Object APBA
APBA is a commonly used abbreviation for "A Prayer Book for Australia," a liturgical text of the Anglican Church of Australia.
 E563042 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: APBA | Statement: [A Prayer Book for Australia, hasAlternativeTitle, APBA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: APBA
Context triple: [A Prayer Book for Australia, hasAlternativeTitle, APBA]
  • A. Sega Sports
    Sega Sports was Sega's sports-focused publishing label known for producing and releasing popular sports video game franchises in the late 1990s and early 2000s.
  • B. BAFA
    BAFA is Germany’s Federal Office for Economic Affairs and Export Control, responsible for implementing economic, energy, and export control policies.
  • C. Palla
    Palla is a Portuguese surname most notably associated with journalist and feminist activist Maria Antónia Palla.
  • D. PES
    PES is a major European political party that unites social-democratic, socialist, and labor parties from across the European Union.
  • E. HarBowl
    HarBowl is the popular nickname for Super Bowl XLVII, which featured a historic matchup between head coach brothers Jim and John Harbaugh.
  • 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: APBA
Triple: [A Prayer Book for Australia, hasAlternativeTitle, APBA]
Generated description
APBA is a commonly used abbreviation for "A Prayer Book for Australia," a liturgical text of the Anglican Church of Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: APBA
Target entity description: APBA is a commonly used abbreviation for "A Prayer Book for Australia," a liturgical text of the Anglican Church of Australia.
  • A. Sega Sports
    Sega Sports was Sega's sports-focused publishing label known for producing and releasing popular sports video game franchises in the late 1990s and early 2000s.
  • B. BAFA
    BAFA is Germany’s Federal Office for Economic Affairs and Export Control, responsible for implementing economic, energy, and export control policies.
  • C. Palla
    Palla is a Portuguese surname most notably associated with journalist and feminist activist Maria Antónia Palla.
  • D. PES
    PES is a major European political party that unites social-democratic, socialist, and labor parties from across the European Union.
  • E. HarBowl
    HarBowl is the popular nickname for Super Bowl XLVII, which featured a historic matchup between head coach brothers Jim and John Harbaugh.
  • 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_69c0087515148190a97475d412563865 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0561121708190a904e52aa3484988 completed March 22, 2026, 8:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11381aa0c81909487a5eb510c9b41 completed March 23, 2026, 10:18 a.m.
NEDg Description generation batch_69c113de5d788190affa46cf416d180d completed March 23, 2026, 10:20 a.m.
NED2 Entity disambiguation (via description) batch_69c1145180008190844d91782929349f completed March 23, 2026, 10:22 a.m.
Created at: March 22, 2026, 4:08 p.m.