Triple

T14525021
Position Surface form Disambiguated ID Type / Status
Subject Table View Beach E340752 entity
Predicate locatedIn P40 FINISHED
Object Table View E340739 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: Table View | Statement: [Table View Beach, locatedIn, Table View]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Table View
Context triple: [Table View Beach, locatedIn, Table View]
  • A. Table View chosen
    Table View is a coastal suburb of Cape Town, South Africa, known for its beaches and panoramic views of Table Mountain.
  • B. TTable
    TTable is a Delphi VCL data-access component that represents and manipulates an entire database table through a live, table-based dataset interface.
  • C. tabla
    The tabla is a pair of hand-played drums central to North Indian classical and folk music, known for its complex rhythms and tonal versatility.
  • D. DataView
    DataView is a low-level JavaScript interface that provides flexible, byte-level read and write access to the contents of an ArrayBuffer, supporting multiple numeric types and endianness.
  • E. DataView
    DataView is ML.NET’s core, schema-aware tabular data abstraction used to efficiently represent and process datasets for machine learning pipelines.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dea04f16f88190ba357b0f8021b46b completed April 14, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5c1bf988190b1265c3db9a6b590 completed May 8, 2026, 12:23 p.m.
Created at: April 10, 2026, 1:22 a.m.