Triple

T21396722
Position Surface form Disambiguated ID Type / Status
Subject Illanun E527804 entity
Predicate sea P2975 FINISHED
Object Sulu Sea NE NERFINISHED

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: Sulu Sea | Statement: [Illanun, sea, Sulu Sea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sulu Sea
Context triple: [Illanun, sea, Sulu Sea]
  • A. Sulu Sea chosen
    The Sulu Sea is a marginal sea in the western Pacific Ocean, located between the Philippines, Malaysia, and Indonesia, known for its rich marine biodiversity and important shipping routes.
  • B. Savu Sea
    The Savu Sea is a small sea in the Lesser Sunda Islands of Indonesia, known for its deep waters, rich marine biodiversity, and location between islands such as Timor, Sumba, and Flores.
  • C. Ceram Sea
    The Ceram Sea is a marginal sea in eastern Indonesia, located between the islands of Seram and Halmahera and forming part of the complex archipelagic waters of the Maluku region.
  • D. Sibuyan Sea
    The Sibuyan Sea is a marginal sea of the western Pacific Ocean in the central Philippines, known as the site of major World War II naval battles and shipwrecks.
  • E. Enshunada Sea
    The Enshunada Sea is a coastal body of water off the Pacific coast of central Japan, bordering Shizuoka and Aichi Prefectures.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b51ff3748190935c0a513c62a12b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b11a2aec8190a60e53b90d0823b1 completed April 22, 2026, 11:29 a.m.
Created at: April 16, 2026, 5:13 p.m.