Triple

T18744899
Position Surface form Disambiguated ID Type / Status
Subject Sulu E458383 entity
Predicate hasMunicipality P847 FINISHED
Object Parang 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: Parang | Statement: [Sulu, hasMunicipality, Parang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parang
Context triple: [Sulu, hasMunicipality, Parang]
  • A. Parang chosen
    Parang is a coastal town in the Philippines that served as a key Allied landing area during the World War II campaign to liberate Mindanao.
  • B. Tekakwitha
    Tekakwitha is the family name of Kateri Tekakwitha, a 17th-century Algonquin–Mohawk woman who became the first Native American saint canonized by the Roman Catholic Church.
  • C. Bago Yoma
    Bago Yoma is a forested mountain range in central Myanmar that forms a natural divide between the Irrawaddy and Sittaung river basins.
  • D. Rigu
    Rigu is a traditional garment worn by women of the Dimasa community, typically characterized by its handwoven fabric and distinctive patterns.
  • E. Mabu
    The Mabu are a peaceful, mole-like race of small, furry humanoids from the Skylanders universe, known for their resourcefulness and close alliance with the Skylanders.
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e57691c8688190b225cbd88493d9d1 completed April 20, 2026, 12:42 a.m.
Created at: April 10, 2026, 11:51 a.m.