Triple

T14786356
Position Surface form Disambiguated ID Type / Status
Subject Meʼen language E347534 entity
Predicate hasExonym P4705 FINISHED
Object Mekan
Mekan is an alternative name used by outsiders for the Meʼen people and their language, an Omotic-speaking ethnic group primarily living in southwestern Ethiopia.
 E1119796 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: Mekan | Statement: [Meʼen language, hasExonym, Mekan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mekan
Context triple: [Meʼen language, hasExonym, Mekan]
  • A. Mekhu
    Mekhu was an ancient Egyptian official and noble whose rock-cut tomb is located among the Tombs of the Nobles at Aswan.
  • B. Mekè
    Mekè is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • C. Kmehin
    Kmehin is a small agricultural community in Israel’s Negev desert, known for its remote desert setting and regional farming activities.
  • D. Meket
    Meket was an ancient Egyptian queen consort of the 11th Dynasty pharaoh Mentuhotep II.
  • E. Mez
    Mez is a music video director known for collaborating with artists like Middle Child to create visually engaging and narrative-driven videos.
  • 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: Mekan
Triple: [Meʼen language, hasExonym, Mekan]
Generated description
Mekan is an alternative name used by outsiders for the Meʼen people and their language, an Omotic-speaking ethnic group primarily living in southwestern Ethiopia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mekan
Target entity description: Mekan is an alternative name used by outsiders for the Meʼen people and their language, an Omotic-speaking ethnic group primarily living in southwestern Ethiopia.
  • A. Mekhu
    Mekhu was an ancient Egyptian official and noble whose rock-cut tomb is located among the Tombs of the Nobles at Aswan.
  • B. Mekè
    Mekè is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • C. Kmehin
    Kmehin is a small agricultural community in Israel’s Negev desert, known for its remote desert setting and regional farming activities.
  • D. Meket
    Meket was an ancient Egyptian queen consort of the 11th Dynasty pharaoh Mentuhotep II.
  • E. Mez
    Mez is a music video director known for collaborating with artists like Middle Child to create visually engaging and narrative-driven videos.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decaa083e481908336d58d026eec32 completed April 14, 2026, 11:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24b9e8a08190bc736ac207b77324 completed May 8, 2026, 6 p.m.
NEDg Description generation batch_69fe266a05308190b9f6adba3e635e2f completed May 8, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_69fe26f8fb7881909892c381b16fc80a completed May 8, 2026, 6:10 p.m.
Created at: April 10, 2026, 1:31 a.m.