Triple

T8992830
Position Surface form Disambiguated ID Type / Status
Subject Sangisari language E214830 entity
Predicate spokenBy P2181 FINISHED
Object Sangisari people
The Sangisari people are an ethnic group from northern Iran, traditionally inhabiting rural areas of Mazandaran and Semnan provinces with a distinct cultural and linguistic heritage.
E786717 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: Sangisari people | Statement: [Sangisari language, spokenBy, Sangisari people]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sangisari people
Context triple: [Sangisari language, spokenBy, Sangisari people]
  • A. Baniata people
    The Baniata people are an indigenous ethnic group of the Solomon Islands, known for their distinct language and traditional cultural practices.
  • B. Shilha people
    The Shilha people are an Amazigh (Berber) ethnic group indigenous to southwestern Morocco, particularly the Sous region and the High Atlas mountains.
  • C. Mararit people
    The Mararit people are an ethnic group of the Sahel region in Chad and Sudan, traditionally speaking a Taman language and practicing agro-pastoralism.
  • D. Gilak people
    The Gilak people are an Iranian ethnic group indigenous to Iran’s northern Caspian Sea region, particularly Gilan Province, known for their distinct Gilaki language and rich local culture.
  • E. Lundayeh people
    The Lundayeh people are an indigenous ethnic group of the highland regions of northern Borneo, known for their distinct language, traditional agriculture, and rich cultural practices closely linked to the interior river valleys.
  • 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: Sangisari people
Triple: [Sangisari language, spokenBy, Sangisari people]
Generated description
The Sangisari people are an ethnic group from northern Iran, traditionally inhabiting rural areas of Mazandaran and Semnan provinces with a distinct cultural and linguistic heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sangisari people
Target entity description: The Sangisari people are an ethnic group from northern Iran, traditionally inhabiting rural areas of Mazandaran and Semnan provinces with a distinct cultural and linguistic heritage.
  • A. Baniata people
    The Baniata people are an indigenous ethnic group of the Solomon Islands, known for their distinct language and traditional cultural practices.
  • B. Shilha people
    The Shilha people are an Amazigh (Berber) ethnic group indigenous to southwestern Morocco, particularly the Sous region and the High Atlas mountains.
  • C. Mararit people
    The Mararit people are an ethnic group of the Sahel region in Chad and Sudan, traditionally speaking a Taman language and practicing agro-pastoralism.
  • D. Gilak people
    The Gilak people are an Iranian ethnic group indigenous to Iran’s northern Caspian Sea region, particularly Gilan Province, known for their distinct Gilaki language and rich local culture.
  • E. Lundayeh people
    The Lundayeh people are an indigenous ethnic group of the highland regions of northern Borneo, known for their distinct language, traditional agriculture, and rich cultural practices closely linked to the interior river valleys.
  • 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_69ca83a05c608190bdfdbdb25e994b39 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6876583081909d936dc3c3152587 completed April 1, 2026, 12:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0773aee148190ad4da1b91271e48c completed April 4, 2026, 2:28 a.m.
NEDg Description generation batch_69d07c2dffd0819096e3614d68ecdcc2 completed April 4, 2026, 2:49 a.m.
NED2 Entity disambiguation (via description) batch_69d07c8549688190a125ef09720c933b completed April 4, 2026, 2:50 a.m.
Created at: March 30, 2026, 7:04 p.m.