Triple

T17194244
Position Surface form Disambiguated ID Type / Status
Subject Bathurst E417304 entity
Predicate hasLandmark P105 FINISHED
Object Arch 22 E358926 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: Arch 22 | Statement: [Bathurst, hasLandmark, Arch 22]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arch 22
Context triple: [Bathurst, hasLandmark, Arch 22]
  • A. Arch 22 chosen
    Arch 22 is a monumental gateway and national landmark in Banjul, The Gambia, commemorating the 1994 military coup and offering panoramic views of the city.
  • B. ARC2
    ARC2 is a deep learning model architecture designed for efficient and accurate text classification tasks.
  • C. Arc 2000
    Arc 2000 is a high-altitude ski resort village in the Les Arcs ski area of the French Alps, known for its extensive slopes and reliable snow conditions.
  • D. the Arch
    The Arch is a deep underwater tunnel and archway in the Blue Hole at Dahab, Egypt, notorious among divers for its beauty and high-risk, often fatal, dive profile.
  • E. Arc 1800
    Arc 1800 is a major purpose-built ski resort village in the Les Arcs area of the French Alps, known for its extensive slopes, lively atmosphere, and modern amenities.
  • 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_69d886d6ba8c819093215917b3d01689 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42da93bf88190b60b658087779d36 completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a015fd5f834819080ad2a2ffdc017b6 completed May 11, 2026, 4:49 a.m.
Created at: April 10, 2026, 5:38 a.m.