Triple

T17891719
Position Surface form Disambiguated ID Type / Status
Subject Covingham E447332 entity
Predicate adjacentTo P224 FINISHED
Object Liden 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: Liden | Statement: [Covingham, adjacentTo, Liden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liden
Context triple: [Covingham, adjacentTo, Liden]
  • A. Liden chosen
    Liden is a residential area and housing estate forming a neighborhood of Stratton St Margaret in Swindon, England.
  • B. Lida
    Lida is a historic city in present-day western Belarus, known for its medieval castle and former role as a regional center in the Grand Duchy of Lithuania.
  • C. Langiden
    Langiden is a rural municipality located in the landlocked province of Abra in the Cordillera region of the Philippines.
  • D. Lidan
    Lidan is a river in southwestern Sweden that flows through the historical province of Västergötland before emptying into Lake Vänern.
  • E. Reiden
    Reiden is a municipality in the canton of Lucerne in Switzerland, situated along the Wigger river.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d7a855c8190b20bdbf6dcd4fd47 completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:19 a.m.