Triple

T5038177
Position Surface form Disambiguated ID Type / Status
Subject KY postcode area E113476 entity
Predicate postTown P2711 FINISHED
Object Leven E6862 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: Leven | Statement: [KY postcode area, postTown, Leven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leven
Context triple: [KY postcode area, postTown, Leven]
  • A. Leven chosen
    Leven is a coastal town in eastern Scotland, situated on the Firth of Forth in the council area of Fife.
  • B. Ederveen
    Ederveen is a village in the Dutch province of Gelderland, known for its rural character and location within the municipality of Ede.
  • C. Bassein
    Bassein is a historic coastal town in western India, now known as Vasai, notable for its strategic port and colonial-era fortifications that played a key role in regional power struggles.
  • D. Wassen
    Wassen is a small Swiss village in the canton of Uri, known for its picturesque church and location along the Gotthard railway and road routes in the central Alps.
  • E. Schwansen
    Schwansen is a rural peninsula in northern Germany situated between the Schlei inlet and the Eckernförde Bay in the state of Schleswig-Holstein.
  • 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_69bd44384298819089c49e7c330ec7b8 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd73daaa788190b670f6c328bfa44f completed March 20, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea479f01c8190a84ff4973845eb17 completed March 21, 2026, 2 p.m.
Created at: March 20, 2026, 1:37 p.m.