Triple

T8237239
Position Surface form Disambiguated ID Type / Status
Subject Romblon E192440 entity
Predicate language P15 FINISHED
Object Onhan
Onhan is an Austronesian language spoken primarily in the province of Romblon in the Philippines.
 E720814 NE FINISHED

How this triple was built (4 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: Onhan | Statement: [Romblon, language, Onhan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Onhan
Context triple: [Romblon, language, Onhan]
  • A. Nahan
    Nahan is a small hill town and municipal council in Himachal Pradesh, India, known for its scenic surroundings, pleasant climate, and role as a regional administrative and commercial center.
  • B. Hannut
    Hannut is a municipality in the French-speaking Walloon Region of Belgium, known for its rural character and location between Liège and Brussels.
  • C. Onhel
    Onhel is a music producer and audio engineer known for his work on major hip-hop projects, including Lil Wayne’s album "Tha Carter V."
  • D. Ahone
    Ahone is the benevolent creator god in the traditional religion of the Powhatan people of Virginia.
  • E. Hona
    Hona is a lesser-known West Chadic language spoken in parts of West Africa, likely within the Hausa-related linguistic area.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Onhan
Triple: [Romblon, language, Onhan]
Generated description
Onhan is an Austronesian language spoken primarily in the province of Romblon in the Philippines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Onhan
Target entity description: Onhan is an Austronesian language spoken primarily in the province of Romblon in the Philippines.
  • A. Nahan
    Nahan is a small hill town and municipal council in Himachal Pradesh, India, known for its scenic surroundings, pleasant climate, and role as a regional administrative and commercial center.
  • B. Hannut
    Hannut is a municipality in the French-speaking Walloon Region of Belgium, known for its rural character and location between Liège and Brussels.
  • C. Onhel
    Onhel is a music producer and audio engineer known for his work on major hip-hop projects, including Lil Wayne’s album "Tha Carter V."
  • D. Ahone
    Ahone is the benevolent creator god in the traditional religion of the Powhatan people of Virginia.
  • E. Hona
    Hona is a lesser-known West Chadic language spoken in parts of West Africa, likely within the Hausa-related linguistic area.
  • F. None of above. chosen

Provenance (5 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_69ca82dc8f148190a2c75a98501a7b91 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb783929c081909db1182947755bae completed March 31, 2026, 7:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd34fb069c8190965d69fae908482e completed April 1, 2026, 3:08 p.m.
NEDg Description generation batch_69cd37a47f3c81909491e9b0316c32f0 completed April 1, 2026, 3:20 p.m.
NED2 Entity disambiguation (via description) batch_69cd4ecc8d68819099932b1ecefc0d36 completed April 1, 2026, 4:58 p.m.
Created at: March 30, 2026, 5:47 p.m.