Triple

T2276313
Position Surface form Disambiguated ID Type / Status
Subject Kes E50778 entity
Predicate languageOfTerm P15 FINISHED
Object Geʽez E205342 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: Geʽez | Statement: [Kes, languageOfTerm, Geʽez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geʽez
Context triple: [Kes, languageOfTerm, Geʽez]
  • A. Geʽez chosen
    Geʽez is an ancient Semitic language of Ethiopia that served as the liturgical and classical language of the Ethiopian Orthodox Church and the ancestor of several modern Ethiopian and Eritrean languages.
  • B. Heruli
    The Heruli were an East Germanic tribal group known for their role in the late Roman Empire’s military and for participating in the migrations and power struggles that reshaped Europe in late antiquity.
  • C. Kumyk
    Kumyk is a Turkic language traditionally spoken by the Kumyk people in the North Caucasus region, particularly in present-day Dagestan, Russia.
  • D. Mingrelians
    Mingrelians are a Kartvelian ethnic group from western Georgia, primarily inhabiting the Samegrelo region and speaking the Mingrelian (Megrelian) language.
  • E. Yekatit
    Yekatit is the sixth month of the Ethiopian calendar, roughly corresponding to February in the Gregorian calendar.
  • 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_69a88b05910c8190a9a2b1ff230c85f9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc1ecc600819095dd4f69af1d18d8 completed March 7, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7f0ed1b881909ba3c7f9fea50267 completed March 9, 2026, 8:04 a.m.
Created at: March 4, 2026, 7:48 p.m.