Triple

T12898277
Position Surface form Disambiguated ID Type / Status
Subject Dusit District E308549 entity
Predicate contains P35 FINISHED
Object Royal Plaza E997582 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: Royal Plaza | Statement: [Dusit District, contains, Royal Plaza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Royal Plaza
Context triple: [Dusit District, contains, Royal Plaza]
  • A. Royal Plaza chosen
    Royal Plaza is a historic public square in Bangkok, Thailand, known for its royal ceremonies and monuments near the Dusit Palace area.
  • B. Park Royal
    Park Royal is a major industrial and business district in northwest London, known as one of the largest industrial estates in Europe and a key regeneration area in the city.
  • C. Plaza Hotel
    The Plaza Hotel is a historic luxury hotel located at the southeast corner of Central Park in Manhattan, renowned for its opulent architecture and frequent appearances in films and literature.
  • D. Grand Plaza
    Grand Plaza is a large, central ceremonial and public space within the ancient Mississippian city of Cahokia, notable for its role in gatherings, rituals, and civic activities.
  • E. Shangri-La Plaza
    Shangri-La Plaza is a premier upscale shopping and lifestyle mall complex located in Mandaluyong, Metro Manila, Philippines.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9717f3fc48190b61c8f6f36cd0725 completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a55f98c08190b8910b1443841fa7 completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:40 p.m.