Triple

T6098977
Position Surface form Disambiguated ID Type / Status
Subject Uma language E135946 entity
Predicate hasDialect P4251 FINISHED
Object Northern Uma
Northern Uma is a regional dialect of the Uma language spoken by communities in Central Sulawesi, Indonesia.
 E570187 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: Northern Uma | Statement: [Uma language, hasDialect, Northern Uma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Northern Uma
Context triple: [Uma language, hasDialect, Northern Uma]
  • A. Southern Uma
    Southern Uma is a regional dialect of the Uma language spoken by a subset of Uma-speaking communities, distinguished by its own phonological and lexical features.
  • B. South Ushba
    South Ushba is one of the twin summits of Mount Ushba in the Caucasus, known among climbers for its steep, challenging routes and dramatic alpine scenery.
  • C. North Ushba
    North Ushba is one of the twin summits of the dramatic, technically challenging Ushba peak in the Caucasus Mountains of Georgia.
  • D. Nain
    Nain is a renowned Iranian town famous for producing high-quality, finely knotted Persian carpets characterized by intricate designs and a typically light color palette.
  • E. Nain
    Nain is a remote coastal town in northern Labrador, Canada, known as the administrative center of the Inuit region of Nunatsiavut.
  • 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: Northern Uma
Triple: [Uma language, hasDialect, Northern Uma]
Generated description
Northern Uma is a regional dialect of the Uma language spoken by communities in Central Sulawesi, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Northern Uma
Target entity description: Northern Uma is a regional dialect of the Uma language spoken by communities in Central Sulawesi, Indonesia.
  • A. Southern Uma
    Southern Uma is a regional dialect of the Uma language spoken by a subset of Uma-speaking communities, distinguished by its own phonological and lexical features.
  • B. South Ushba
    South Ushba is one of the twin summits of Mount Ushba in the Caucasus, known among climbers for its steep, challenging routes and dramatic alpine scenery.
  • C. North Ushba
    North Ushba is one of the twin summits of the dramatic, technically challenging Ushba peak in the Caucasus Mountains of Georgia.
  • D. Nain
    Nain is a renowned Iranian town famous for producing high-quality, finely knotted Persian carpets characterized by intricate designs and a typically light color palette.
  • E. Nain
    Nain is a remote coastal town in northern Labrador, Canada, known as the administrative center of the Inuit region of Nunatsiavut.
  • 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_69c0087cd3c48190b459848c72d84eb1 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05a9a02888190ac201acd14c3fc31 completed March 22, 2026, 9:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1358d0e18819084e2acb9e75271b4 completed March 23, 2026, 12:43 p.m.
NEDg Description generation batch_69c1362a78548190b3ccbc9089821b40 completed March 23, 2026, 12:46 p.m.
NED2 Entity disambiguation (via description) batch_69c1368d452c8190bc713c0f508250a8 completed March 23, 2026, 12:48 p.m.
Created at: March 22, 2026, 4:13 p.m.