Triple

T15337026
Position Surface form Disambiguated ID Type / Status
Subject Roma, Queensland E366692 entity
Predicate airportIATAcode P418 FINISHED
Object RMA
RMA is the IATA airport code for Roma Airport, a regional airport serving the town of Roma in Queensland, Australia.
 E1150877 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: RMA | Statement: [Roma, Queensland, airportIATAcode, RMA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: RMA
Context triple: [Roma, Queensland, airportIATAcode, RMA]
  • A. RMA
    RMA is a U.S. Department of Agriculture agency responsible for overseeing federal crop insurance and risk management programs for farmers and ranchers.
  • B. RMA
    RMA is New Zealand’s principal environmental and resource management law that governs how natural and physical resources are used, developed, and protected.
  • C. RM
    RM is a UK postcode area in east London and parts of Essex, covering districts such as Romford and surrounding suburbs.
  • D. RM
    RM is the currency symbol that was used to denote the German Reichsmark, the former official currency of Germany from 1924 to 1948.
  • E. RM
    RM is a South Korean rapper, songwriter, and leader of the globally renowned K-pop group BTS.
  • 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: RMA
Triple: [Roma, Queensland, airportIATAcode, RMA]
Generated description
RMA is the IATA airport code for Roma Airport, a regional airport serving the town of Roma in Queensland, Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: RMA
Target entity description: RMA is the IATA airport code for Roma Airport, a regional airport serving the town of Roma in Queensland, Australia.
  • A. RMA
    RMA is a U.S. Department of Agriculture agency responsible for overseeing federal crop insurance and risk management programs for farmers and ranchers.
  • B. RMA
    RMA is New Zealand’s principal environmental and resource management law that governs how natural and physical resources are used, developed, and protected.
  • C. RM
    RM is a UK postcode area in east London and parts of Essex, covering districts such as Romford and surrounding suburbs.
  • D. RM
    RM is the currency symbol that was used to denote the German Reichsmark, the former official currency of Germany from 1924 to 1948.
  • E. RM
    RM is a South Korean rapper, songwriter, and leader of the globally renowned K-pop group BTS.
  • 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_69d85a1355608190a6673ddb67231d54 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e11b22c81908280efe65acd5454 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01f11b88819089342e8b088bc95e completed May 9, 2026, 9:44 a.m.
NEDg Description generation batch_69ff02de46948190ac9b9f87313a8442 completed May 9, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_69ff0341238c8190a7d0473ad9ab702c completed May 9, 2026, 9:49 a.m.
Created at: April 10, 2026, 3:17 a.m.