Triple

T20234666
Position Surface form Disambiguated ID Type / Status
Subject Cordova, Cebu E495618 entity
Predicate isIn P1393 FINISHED
Object Mactan Island 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: Mactan Island | Statement: [Cordova, Cebu, isIn, Mactan Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mactan Island
Context triple: [Cordova, Cebu, isIn, Mactan Island]
  • A. Mactan chosen
    Mactan is a Philippine island historically renowned as the site where Portuguese explorer Ferdinand Magellan was killed in battle in 1521.
  • B. Siquijor Island
    Siquijor Island is a small Philippine island province in the central Visayas region, known for its white-sand beaches, coral reefs, and folklore surrounding mysticism and traditional healing.
  • C. Bohol Island
    Bohol Island is a popular island province in the central Philippines known for its Chocolate Hills, tarsier sanctuaries, and white-sand beaches.
  • D. Masbate Island
    Masbate Island is a large island in the central Philippines known for its cattle ranches, rolling hills, and role as the main island of Masbate Province.
  • E. Catanduanes Island
    Catanduanes Island is a typhoon-prone, largely rural island province in the Bicol Region of the Philippines, known for its rugged coastlines, surfing beaches, and lush mountainous interior.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e67167fae88190a26ff10d698174f8 completed April 20, 2026, 6:33 p.m.
Created at: April 11, 2026, 11:40 p.m.