Triple

T15006746
Position Surface form Disambiguated ID Type / Status
Subject Australian Bureau of Statistics E377729 entity
Predicate abbreviation P43 FINISHED
Object ABS
ABS is Australia’s national statistical agency responsible for collecting, analyzing, and publishing key economic, demographic, and social data.
 E1131913 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: ABS | Statement: [Australian Bureau of Statistics, abbreviation, ABS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ABS
Context triple: [Australian Bureau of Statistics, abbreviation, ABS]
  • A. ABS
    ABS is the stock ticker symbol for ABS-CBN Corporation, a major Philippine media and entertainment company.
  • B. ABS
    ABS (Anti-lock Braking System) is a vehicle safety technology that prevents the wheels from locking during braking to maintain steering control and reduce stopping distances on slippery surfaces.
  • C. ABL
    ABL is the commonly used abbreviation for the Academia Brasileira de Letras, Brazil’s foremost literary and language academy.
  • D. ABL
    ABL is the IATA airport code assigned to Ambrolauri Airport in Georgia.
  • E. ABL
    ABL was a short-lived professional American basketball league that operated in the mid-1940s, preceding the formation of the NBA.
  • 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: ABS
Triple: [Australian Bureau of Statistics, abbreviation, ABS]
Generated description
ABS is Australia’s national statistical agency responsible for collecting, analyzing, and publishing key economic, demographic, and social data.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ABS
Target entity description: ABS is Australia’s national statistical agency responsible for collecting, analyzing, and publishing key economic, demographic, and social data.
  • A. ABS
    ABS is the stock ticker symbol for ABS-CBN Corporation, a major Philippine media and entertainment company.
  • B. ABS
    ABS (Anti-lock Braking System) is a vehicle safety technology that prevents the wheels from locking during braking to maintain steering control and reduce stopping distances on slippery surfaces.
  • C. ABL
    ABL is the commonly used abbreviation for the Academia Brasileira de Letras, Brazil’s foremost literary and language academy.
  • D. ABL
    ABL is the IATA airport code assigned to Ambrolauri Airport in Georgia.
  • E. ABL
    ABL was a short-lived professional American basketball league that operated in the mid-1940s, preceding the formation of the NBA.
  • 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_69d85cd3a3c881908c71fc424d459c17 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded73348d4819091d9e7f1b0fed822 completed April 15, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe96a35acc8190a85f2ce32800ce1b completed May 9, 2026, 2:06 a.m.
NEDg Description generation batch_69fe98917abc81908998205b4ecf201f completed May 9, 2026, 2:14 a.m.
NED2 Entity disambiguation (via description) batch_69fe997c744481909bd3c66c3dd68f19 completed May 9, 2026, 2:18 a.m.
Created at: April 10, 2026, 2:54 a.m.