Triple

T1194355
Position Surface form Disambiguated ID Type / Status
Subject Indo-Iranian languages E25632 entity
Predicate includesLanguage P2177 FINISHED
Object Luri
Luri is a Southwestern Iranian language spoken primarily by the Lur people in western and southwestern Iran.
 E159563 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: Luri | Statement: [Indo-Iranian languages, includesLanguage, Luri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Luri
Context triple: [Indo-Iranian languages, includesLanguage, Luri]
  • A. Lemi
    Lemi is a small rural municipality in southeastern Finland known for its lakes, forests, and traditional Karelian culture.
  • B. Jandali
    Jandali is an Arabic family name most notably associated with Abdulfattah Jandali, the biological father of Apple co-founder Steve Jobs.
  • C. Urunga
    Urunga is a small coastal town in New South Wales, Australia, known for its scenic boardwalks, estuary views, and relaxed seaside atmosphere.
  • D. Yahi
    The Yahi were a small Native American group from northern California, known for being among the last surviving independent Indigenous peoples in the region and for the story of Ishi, their last known member.
  • E. Arida
    Arida is a city in Japan known for its agricultural production, particularly high-quality citrus fruits, within Wakayama Prefecture.
  • 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: Luri
Triple: [Indo-Iranian languages, includesLanguage, Luri]
Generated description
Luri is a Southwestern Iranian language spoken primarily by the Lur people in western and southwestern Iran.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Luri
Target entity description: Luri is a Southwestern Iranian language spoken primarily by the Lur people in western and southwestern Iran.
  • A. Lemi
    Lemi is a small rural municipality in southeastern Finland known for its lakes, forests, and traditional Karelian culture.
  • B. Jandali
    Jandali is an Arabic family name most notably associated with Abdulfattah Jandali, the biological father of Apple co-founder Steve Jobs.
  • C. Urunga
    Urunga is a small coastal town in New South Wales, Australia, known for its scenic boardwalks, estuary views, and relaxed seaside atmosphere.
  • D. Yahi
    The Yahi were a small Native American group from northern California, known for being among the last surviving independent Indigenous peoples in the region and for the story of Ishi, their last known member.
  • E. Arida
    Arida is a city in Japan known for its agricultural production, particularly high-quality citrus fruits, within Wakayama Prefecture.
  • 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_69a49429f5ec8190a6a205eb0ae81e5e completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd7743548190a70d3f3c7378aaa7 completed March 1, 2026, 10:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69acde099eb88190ac354f3b4efb0965 completed March 8, 2026, 2:25 a.m.
NEDg Description generation batch_69acde7990b4819082a1bcb50215d4f1 completed March 8, 2026, 2:27 a.m.
NED2 Entity disambiguation (via description) batch_69acdee2d71481908a735d5685693ca8 completed March 8, 2026, 2:28 a.m.
Created at: March 1, 2026, 7:46 p.m.