Triple

T16900154
Position Surface form Disambiguated ID Type / Status
Subject Koko Nor E424412 entity
Predicate hasIsland P970 FINISHED
Object Bird Island E1241780 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: Bird Island | Statement: [Koko Nor, hasIsland, Bird Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bird Island
Context triple: [Koko Nor, hasIsland, Bird Island]
  • A. Bird Island
    Bird Island is a small South African island in Algoa Bay known for its large seabird colonies and important marine wildlife habitat.
  • B. Bird Island
    Bird Island, also known as Chidiya Tapu, is a scenic coastal spot in the Andaman Islands famed for its rich birdlife and sunset views.
  • C. Bird Island
    Bird Island is a small rocky islet off the southern Oregon coast known for providing nesting habitat to seabirds and other marine wildlife.
  • D. Bird Island
    Bird Island is the fictional home of the bird characters in the Angry Birds franchise, prominently featured as the main setting in The Angry Birds Movie.
  • E. Bird Island chosen
    Bird Island is a small, wildlife-rich island in Qinghai Lake in China, famed as a major breeding and migratory stopover site for numerous bird species.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3c8dbc6e48190be90066b82fc61db completed April 18, 2026, 6:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00d45647f481908ae76a0b8fe8a9cb completed May 10, 2026, 6:54 p.m.
Created at: April 10, 2026, 5:29 a.m.