Triple

T5307151
Position Surface form Disambiguated ID Type / Status
Subject Sci-Fi City E120129 entity
Predicate locatedIn P40 FINISHED
Object Sentosa E268301 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: Sentosa | Statement: [Sci-Fi City, locatedIn, Sentosa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sentosa
Context triple: [Sci-Fi City, locatedIn, Sentosa]
  • A. Sentosa Island chosen
    Sentosa Island is a popular resort island in Singapore known for its theme parks, beaches, and entertainment attractions.
  • B. Sentosa Gateway
    Sentosa Gateway is the main access road and bridge connecting mainland Singapore to Sentosa Island, serving as a key entry point to its attractions and resorts.
  • C. Resorts World Sentosa
    Resorts World Sentosa is a major integrated resort on Singapore’s Sentosa Island, featuring hotels, a casino, theme parks, and various entertainment and dining attractions.
  • D. Stonecutters Island
    Stonecutters Island is a reclaimed island in Hong Kong known for its strategic location in Victoria Harbour and major sewage treatment and military facilities.
  • E. Changi Beach
    Changi Beach is a coastal area in Singapore historically known as one of the main sites of mass executions during the Sook Ching massacre in World War II.
  • 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_69bd44704be88190acdb2ac481b0ff55 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd851ee8908190814b695723247016 completed March 20, 2026, 5:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf10fb59ac8190ad23ea4f77a8c0e7 completed March 21, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:53 p.m.