Triple

T9217623
Position Surface form Disambiguated ID Type / Status
Subject Linus Sandgren E221279 entity
Predicate workedOn P3 FINISHED
Object Small Apartments E572663 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: Small Apartments | Statement: [Linus Sandgren, workedOn, Small Apartments]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Small Apartments
Context triple: [Linus Sandgren, workedOn, Small Apartments]
  • A. Small Apartments chosen
    Small Apartments is a dark comedy film directed by Jonas Åkerlund, known for its eccentric characters and offbeat, macabre humor.
  • B. Small
    Small is a peer-reviewed scientific journal focusing on nanoscience and nanotechnology, including research on nanoscale materials, devices, and systems.
  • C. Little Building
    The Little Building is a prominent Emerson College residence and academic facility in Boston, known for its historic architecture and central role in campus life.
  • D. Villete
    Villete is a fictional town in Charlotte Brontë’s novel of the same name, serving as the atmospheric setting for Lucy Snowe’s experiences in a girls’ boarding school.
  • E. Small Baths
    Small Baths is a bathing complex within Hadrian’s Villa at Tivoli, notable for its intimate scale and sophisticated Roman architectural and decorative features.
  • 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_69ca83eae42c8190a0ea9e040710a277 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccda0ae3d081908ff3f5dab52df5ae completed April 1, 2026, 8:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0662427dc81908cb9bfacc5b9e0f5 completed April 4, 2026, 1:15 a.m.
Created at: March 30, 2026, 7:27 p.m.