Triple

T10441166
Position Surface form Disambiguated ID Type / Status
Subject Husum E246172 entity
Predicate hasLandmark P105 FINISHED
Object Husum harbor E246172 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: Husum harbor | Statement: [Husum, hasLandmark, Husum harbor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Husum harbor
Context triple: [Husum, hasLandmark, Husum harbor]
  • A. Schleswig harbor
    Schleswig harbor is a small historic port and marina in the town of Schleswig on the Schlei inlet in northern Germany.
  • B. Husum chosen
    Husum is a small coastal town in northern Germany known for its North Sea harbor, maritime heritage, and role as a local cultural and commercial center.
  • C. Frederikshavn Harbour
    Frederikshavn Harbour is a major commercial and ferry port in the town of Frederikshavn in northern Denmark, serving as an important maritime hub for traffic across the Kattegat and to Norway and Sweden.
  • D. Korsør Harbour
    Korsør Harbour is a Danish port on the Great Belt known historically as a strategic maritime hub and naval base area.
  • E. Nyborg Harbour
    Nyborg Harbour is a Danish port facility in the coastal town of Nyborg on the island of Funen, serving local maritime traffic, fishing, and recreational boating.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fb9df6fc8190830f405ef955d64b completed April 7, 2026, 12:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69d87ed6edd88190afd5063daba58a46 completed April 10, 2026, 4:38 a.m.
Created at: April 6, 2026, 12:15 p.m.