Triple

T17225235
Position Surface form Disambiguated ID Type / Status
Subject Queensland Art Gallery E418096 entity
Predicate hasAbbreviation P43 FINISHED
Object QAG
QAG is a major public art museum in Brisbane, Australia, renowned for its extensive collection of Australian and international art and its role within the Queensland Art Gallery | Gallery of Modern Art (QAGOMA) precinct.
 E1257527 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: QAG | Statement: [Queensland Art Gallery, hasAbbreviation, QAG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: QAG
Context triple: [Queensland Art Gallery, hasAbbreviation, QAG]
  • A. GRQ
    GRQ is the IATA airport code for Groningen Airport Eelde, a regional airport serving the city of Groningen and the northern Netherlands.
  • B. QG
    QG is the IATA airline designator for Citilink, a low-cost carrier based in Indonesia.
  • C. QG
    QG is the abbreviation for the Quetta Gladiators, a professional Twenty20 cricket franchise that competes in Pakistan's Super League.
  • D. AQ
    AQ is an Oracle Database feature that provides message-based communication and queuing capabilities for building asynchronous, distributed applications.
  • E. AQ
    AQ is the Italian vehicle registration code assigned to the province of L'Aquila in the Abruzzo region.
  • 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: QAG
Triple: [Queensland Art Gallery, hasAbbreviation, QAG]
Generated description
QAG is a major public art museum in Brisbane, Australia, renowned for its extensive collection of Australian and international art and its role within the Queensland Art Gallery | Gallery of Modern Art (QAGOMA) precinct.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: QAG
Target entity description: QAG is a major public art museum in Brisbane, Australia, renowned for its extensive collection of Australian and international art and its role within the Queensland Art Gallery | Gallery of Modern Art (QAGOMA) precinct.
  • A. GRQ
    GRQ is the IATA airport code for Groningen Airport Eelde, a regional airport serving the city of Groningen and the northern Netherlands.
  • B. QG
    QG is the IATA airline designator for Citilink, a low-cost carrier based in Indonesia.
  • C. QG
    QG is the abbreviation for the Quetta Gladiators, a professional Twenty20 cricket franchise that competes in Pakistan's Super League.
  • D. AQ
    AQ is the Italian vehicle registration code assigned to the province of L'Aquila in the Abruzzo region.
  • E. AQ
    AQ is an Oracle Database feature that provides message-based communication and queuing capabilities for building asynchronous, distributed applications.
  • 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42de0a8dc819093d9c8fb4f80342c completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01675cc70881909cf39b2e229f5d1e completed May 11, 2026, 5:21 a.m.
NEDg Description generation batch_6a016a5f58408190b42a8da742aa2f5b completed May 11, 2026, 5:34 a.m.
NED2 Entity disambiguation (via description) batch_6a016b0e72588190b1ba2b45f0425d3d completed May 11, 2026, 5:37 a.m.
Created at: April 10, 2026, 5:38 a.m.