Triple

T10043058
Position Surface form Disambiguated ID Type / Status
Subject Geʽez E205342 entity
Predicate ISO639-3Code P208 FINISHED
Object gez
gez is the ISO 639-3 code for Geʽez, an ancient Semitic language of Ethiopia that serves as the liturgical language of the Ethiopian and Eritrean Orthodox churches.
 E837593 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: gez | Statement: [Geʽez, ISO639-3Code, gez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: gez
Context triple: [Geʽez, ISO639-3Code, gez]
  • A. Geg
    Geg is an alternative name for Gheg, the northern dialect group of the Albanian language spoken primarily in northern Albania and surrounding regions.
  • B. Giez
    Giez is a small municipality in the canton of Vaud in western Switzerland, situated near the town of Grandson and close to Lake Neuchâtel.
  • C. .ge
    .ge is the country code top-level domain (ccTLD) assigned to websites associated with Georgia.
  • D. GEG
    GEG is the three-letter IATA airport code for Spokane International Airport in Spokane, Washington.
  • E. gezaixi
    Gezaixi is a traditional form of Taiwanese opera that combines singing, dialogue, and stylized movement to tell folk and historical stories on stage.
  • 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: gez
Triple: [Geʽez, ISO639-3Code, gez]
Generated description
gez is the ISO 639-3 code for Geʽez, an ancient Semitic language of Ethiopia that serves as the liturgical language of the Ethiopian and Eritrean Orthodox churches.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: gez
Target entity description: gez is the ISO 639-3 code for Geʽez, an ancient Semitic language of Ethiopia that serves as the liturgical language of the Ethiopian and Eritrean Orthodox churches.
  • A. Geg
    Geg is an alternative name for Gheg, the northern dialect group of the Albanian language spoken primarily in northern Albania and surrounding regions.
  • B. Giez
    Giez is a small municipality in the canton of Vaud in western Switzerland, situated near the town of Grandson and close to Lake Neuchâtel.
  • C. .ge
    .ge is the country code top-level domain (ccTLD) assigned to websites associated with Georgia.
  • D. GEG
    GEG is the three-letter IATA airport code for Spokane International Airport in Spokane, Washington.
  • E. gezaixi
    Gezaixi is a traditional form of Taiwanese opera that combines singing, dialogue, and stylized movement to tell folk and historical stories on stage.
  • 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_69ca834f70e88190b2d74828b7767ec1 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cdcf60a2208190846e57b5f5649307 completed April 2, 2026, 2:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d28278235c8190a5e833a9586bd3f5 completed April 5, 2026, 3:40 p.m.
NEDg Description generation batch_69d28391f8fc8190964cdccaf5625617 completed April 5, 2026, 3:45 p.m.
NED2 Entity disambiguation (via description) batch_69d284604dc88190b452ee847d3390dd completed April 5, 2026, 3:48 p.m.
Created at: March 30, 2026, 8:55 p.m.