Triple

T10643005
Position Surface form Disambiguated ID Type / Status
Subject Hill Mari E250768 entity
Predicate ancestor P5206 FINISHED
Object Proto-Mari
Proto-Mari is the reconstructed ancestral language from which the modern Hill Mari language developed.
E877902 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: Proto-Mari | Statement: [Hill Mari, ancestor, Proto-Mari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Proto-Mari
Context triple: [Hill Mari, ancestor, Proto-Mari]
  • A. Proto-Chadic
    Proto-Chadic is the reconstructed common ancestor of the Chadic branch of the Afroasiatic language family, from which languages like Dass are believed to have descended.
  • B. Colchidian languages
    Colchidian languages are a subgroup of the Kartvelian language family spoken in western Georgia, including varieties such as Mingrelian and Laz.
  • C. Khazar language
    The Khazar language was the now-extinct Turkic tongue once spoken by the Khazar Khaganate, belonging to the Oghur branch of the Turkic language family.
  • D. Hurro-Urartian
    Hurro-Urartian is a proposed ancient language family that groups together the Hurrian and Urartian languages once spoken in the Near East.
  • E. Scythian languages
    Scythian languages are an extinct group of ancient Eastern Iranian languages once spoken by the nomadic Scythian peoples across the Eurasian steppe.
  • 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: Proto-Mari
Triple: [Hill Mari, ancestor, Proto-Mari]
Generated description
Proto-Mari is the reconstructed ancestral language from which the modern Hill Mari language developed.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Proto-Mari
Target entity description: Proto-Mari is the reconstructed ancestral language from which the modern Hill Mari language developed.
  • A. Proto-Chadic
    Proto-Chadic is the reconstructed common ancestor of the Chadic branch of the Afroasiatic language family, from which languages like Dass are believed to have descended.
  • B. Colchidian languages
    Colchidian languages are a subgroup of the Kartvelian language family spoken in western Georgia, including varieties such as Mingrelian and Laz.
  • C. Khazar language
    The Khazar language was the now-extinct Turkic tongue once spoken by the Khazar Khaganate, belonging to the Oghur branch of the Turkic language family.
  • D. Hurro-Urartian
    Hurro-Urartian is a proposed ancient language family that groups together the Hurrian and Urartian languages once spoken in the Near East.
  • E. Scythian languages
    Scythian languages are an extinct group of ancient Eastern Iranian languages once spoken by the nomadic Scythian peoples across the Eurasian steppe.
  • 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_69d6aa5a4c4881908f39be6efe5981e5 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6dfcf65fc81909a0c86daefaab1ab completed April 8, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69d97a4555e48190be39c0a7698b4282 completed April 10, 2026, 10:31 p.m.
NEDg Description generation batch_69d97cc07100819088683a0d79b2baa0 completed April 10, 2026, 10:42 p.m.
NED2 Entity disambiguation (via description) batch_69d97e0cda0c8190af5013b971b2ad3c completed April 10, 2026, 10:47 p.m.
Created at: April 8, 2026, 9:05 p.m.