Triple

T20895147
Position Surface form Disambiguated ID Type / Status
Subject Tegeler Hafen E514512 entity
Predicate locatedIn P40 FINISHED
Object Tegel 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: Tegel | Statement: [Tegeler Hafen, locatedIn, Tegel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tegel
Context triple: [Tegeler Hafen, locatedIn, Tegel]
  • A. Tegel chosen
    Tegel is a locality in the Reinickendorf borough of Berlin, Germany, historically known for its manor associated with the Humboldt family and later for the former Berlin Tegel Airport.
  • B. Schönefeld
    Schönefeld is a municipality just southeast of Berlin in the German state of Brandenburg, known for hosting the Berlin Brandenburg Airport.
  • C. Tempelhof Airport
    Tempelhof Airport is a historic Berlin airfield best known as a central hub of the Berlin Airlift during the Cold War.
  • D. Tempelhof
    Tempelhof is a historic district in Berlin, Germany, best known for the former Tempelhof Airport and its vast airfield now used as a public park.
  • E. Berlin Schönefeld Airport
    Berlin Schönefeld Airport was Berlin’s former secondary international airport located southeast of the city, which was eventually incorporated into the new Berlin Brandenburg Airport complex.
  • 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d06129788190b88ab807af4641c1 completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:47 p.m.