Triple

T23478372
Position Surface form Disambiguated ID Type / Status
Subject Hamina E570331 entity
Predicate hasLandmark P105 FINISHED
Object Hamina Town Hall 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: Hamina Town Hall | Statement: [Hamina, hasLandmark, Hamina Town Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hamina Town Hall
Context triple: [Hamina, hasLandmark, Hamina Town Hall]
  • A. Hamina Town Hall chosen
    Hamina Town Hall is a historic municipal building in the Finnish town of Hamina, notable for its central location and traditional architecture.
  • B. Oujda City Hall
    Oujda City Hall is the main municipal government building and administrative center of the city of Oujda in northeastern Morocco.
  • C. El Mouradia Palace
    El Mouradia Palace is the official presidential residence and seat of executive power in Algiers, Algeria.
  • D. City Hall of Tunis
    The City Hall of Tunis is the main municipal government building of Tunisia’s capital, located in the historic Kasbah district and serving as the administrative center of the city.
  • E. Hassan Tower
    Hassan Tower is an unfinished 12th-century minaret and iconic historical monument in Rabat, Morocco, originally intended to be the world’s largest mosque.
  • 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_69e245af8a88819084f2704f6d265a92 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a74e7e648190b89006dce7d7ce05 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:02 p.m.