Triple

T14247780
Position Surface form Disambiguated ID Type / Status
Subject Waverley railway station E353179 entity
Predicate stationCode P1289 FINISHED
Object EDB E58615 NE FINISHED

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: EDB | Statement: [Waverley railway station, stationCode, EDB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EDB
Context triple: [Waverley railway station, stationCode, EDB]
  • A. EDB
    EDB is the government department in Hong Kong responsible for formulating and implementing education policies and overseeing the education system.
  • B. EDB chosen
    EDB is the National Rail station code for Edinburgh Waverley, the main railway station in Edinburgh, Scotland.
  • C. ERDB
    ERDB is a Philippine government bureau focused on conducting research and development to support the sustainable management and conservation of the country’s ecosystems and natural resources.
  • D. ETDB
    ETDB is a regional international financial institution focused on promoting economic development and cooperation among its member states through trade and investment financing.
  • E. BDB
    BDB is the IATA airport code for Bundaberg Airport, a regional airport serving the city of Bundaberg in Queensland, Australia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8278c43e08190824146f4632b89a5 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6295ef9081909cfb0c1283bca21a completed April 14, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd282571ec819080d187ecec3ed925 completed May 8, 2026, 12:02 a.m.
Created at: April 10, 2026, 1:08 a.m.