Triple

T10747745
Position Surface form Disambiguated ID Type / Status
Subject Dauin E253493 entity
Predicate language P15 FINISHED
Object Cebuano E7565 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: Cebuano | Statement: [Dauin, language, Cebuano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cebuano
Context triple: [Dauin, language, Cebuano]
  • A. Cebuano language chosen
    The Cebuano language is an Austronesian language widely spoken in the southern Philippines, particularly in the Visayas and parts of Mindanao.
  • B. Binisaya
    Binisaya is a major Austronesian language of the Philippines, widely spoken in the Central Visayas and parts of Mindanao.
  • C. Tagalog
    Tagalog is an Austronesian language primarily spoken in the Philippines and serves as the basis for the country’s national language, Filipino.
  • D. Waray language
    Waray is an Austronesian language spoken primarily in the Eastern Visayas region of the Philippines, particularly on Samar and nearby islands.
  • E. Hiligaynon language
    Hiligaynon is a major Austronesian language of the Philippines, widely spoken in Western Visayas and parts of Mindanao, particularly in and around Iloilo and Negros Occidental.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d711b9242c81908dbf3fa155159b3c completed April 9, 2026, 2:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69de231af7388190b73347a3ffc1077a completed April 14, 2026, 11:20 a.m.
Created at: April 8, 2026, 9:15 p.m.