Triple

T16158265
Position Surface form Disambiguated ID Type / Status
Subject Graben E392108 entity
Predicate hasLandmark P105 FINISHED
Object Ankerhaus E1117263 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: Ankerhaus | Statement: [Graben, hasLandmark, Ankerhaus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ankerhaus
Context triple: [Graben, hasLandmark, Ankerhaus]
  • A. Ankerhaus chosen
    Ankerhaus is a notable historic building in Vienna, Austria, recognized for its distinctive architecture and prominent location on the Graben.
  • B. Lucknerhaus
    Lucknerhaus is a mountain hut and popular starting point for alpine tours in the Austrian Alps, particularly in the Großglockner area.
  • C. Almenhof
    Almenhof is a residential district of Mannheim in the German state of Baden-Württemberg.
  • D. Woermannhaus
    Woermannhaus is a historic German colonial-era building in Swakopmund, Namibia, known for its distinctive architecture and prominent tower.
  • E. Fischerhäuser
    Fischerhäuser is a small locality that forms part of the municipality of Inning am Ammersee in Bavaria, Germany.
  • 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21e5c9cd0819090e34ee163ffb118 completed April 17, 2026, 11:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7b05a588190a44d1c922195a87b completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5:01 a.m.