Triple

T16458715
Position Surface form Disambiguated ID Type / Status
Subject Elis E399749 entity
Predicate contains P35 FINISHED
Object Olympia E33311 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: Olympia | Statement: [Elis, contains, Olympia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Olympia
Context triple: [Elis, contains, Olympia]
  • A. Olympia chosen
    Olympia is an ancient sanctuary in Greece renowned as a major religious center dedicated to Zeus and the original site of the Olympic Games.
  • B. Olympia
    Olympia is the capital city of Washington State, located at the southern end of Puget Sound and known as a regional center for government and culture.
  • C. Olympia
    Olympia is a 1938 German documentary film directed by Leni Riefenstahl that chronicles the 1936 Berlin Olympic Games and is renowned both for its pioneering cinematic techniques and its association with Nazi propaganda.
  • D. Olympia
    Olympia is a prestigious international bodybuilding competition title awarded annually to the world's top professional bodybuilders.
  • E. Olympia
    Olympia is a prominent football stadium in Helsingborg, Sweden, serving as the home ground of Helsingborgs IF.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32d7ff0e881909100bb5b33c04291 completed April 18, 2026, 7:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f51d93081909ede0adcf8e604d4 completed May 10, 2026, 9:26 a.m.
Created at: April 10, 2026, 5:10 a.m.