Triple

T22230963
Position Surface form Disambiguated ID Type / Status
Subject Ratmalana E549463 entity
Predicate airportIATACode P418 FINISHED
Object RML NE NERFINISHED

How this triple was built (2 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: RML | Statement: [Ratmalana, airportIATACode, RML]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RML
Context triple: [Ratmalana, airportIATACode, RML]
  • A. RML chosen
    RML is the IATA airport code for Ratmalana Airport, a domestic and regional airport serving the Colombo area in Sri Lanka.
  • B. RMLAU
    RMLAU is a public state university located in Ayodhya, Uttar Pradesh, India, offering undergraduate and postgraduate programs across various disciplines.
  • C. RMLI
    RMLI is a museum dedicated to preserving and interpreting the railroad history and heritage of Long Island, New York.
  • D. RLM
    RLM was the abbreviation for the Reich Air Ministry, the government department responsible for overseeing aviation and the Luftwaffe in Nazi Germany.
  • E. RMG
    RMG is the stock ticker symbol for Royal Mail Group, the United Kingdom’s historic postal and delivery services company, on the London Stock Exchange.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf2a26c81908aaf614d7c75e219 completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:37 p.m.