Triple

T3612861
Position Surface form Disambiguated ID Type / Status
Subject Eureka E76528 entity
Predicate shipName P14494 FINISHED
Object Eureka E76528 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: Eureka | Statement: [Eureka, shipName, Eureka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eureka
Context triple: [Eureka, shipName, Eureka]
  • A. Eureka
    Eureka is the codename for the Eureka Conference, a World War II meeting between Allied leaders Franklin D. Roosevelt, Winston Churchill, and Joseph Stalin held in Tehran in 1943.
  • B. Eureka chosen
    Eureka is a historic side-wheel paddle steamboat and former ferry now preserved as a museum ship in San Francisco.
  • C. Eureka
    Eureka is a historic coastal city in Northern California known for its Victorian architecture, maritime heritage, and role as a regional cultural and economic center.
  • D. Eureka
    Eureka is a science fiction television series that follows the quirky residents of a secret high-tech town where brilliant scientists’ experiments frequently go awry.
  • E. Eureka
    Eureka is an experimental rock and avant-garde album by American musician and producer Jim O'Rourke, noted for its intricate arrangements and genre-blending sound.
  • 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_69ad85da0ba481908b3b48c69efe2b98 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc2786f808190be4e42734a79d74e completed March 8, 2026, 6:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b43316224081909372f1007becc663 completed March 13, 2026, 3:53 p.m.
Created at: March 8, 2026, 3:23 p.m.