Triple

T14040287
Position Surface form Disambiguated ID Type / Status
Subject Pontivy E337826 entity
Predicate hasTwinTown P919 FINISHED
Object Minden E960739 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: Minden | Statement: [Pontivy, hasTwinTown, Minden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Minden
Context triple: [Pontivy, hasTwinTown, Minden]
  • A. Minden
    Minden is a historic German city in North Rhine-Westphalia known for its strategic location on the Weser River and its well-preserved old town.
  • B. Minden chosen
    Minden is a small city in northwestern Louisiana known for its historic downtown, antebellum homes, and role as the seat of Webster Parish.
  • C. Minden, Iowa
    Minden, Iowa is a small rural city located in western Iowa within Pottawattamie County.
  • D. Minden, Nevada
    Minden, Nevada is a small unincorporated town in western Nevada known as a historic community in the Carson Valley near the Sierra Nevada.
  • E. Dulus
    Dulus is a bird genus best known for the palmchat, a highly social songbird endemic to Hispaniola and the sole member of its family, Dulidae.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de30ee374081908b6b5e8f81dd90f2 completed April 14, 2026, 12:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc33dbc8c819080b6cb3d589da7a1 completed May 6, 2026, 10:39 p.m.
Created at: April 9, 2026, 10:20 p.m.