Triple
T13040846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Golestan Province |
E327185
|
entity |
| Predicate | hasEthnicGroup |
P1898
|
FINISHED |
| Object |
Lari
The Lari are an Iranian ethnic group traditionally inhabiting parts of southern and southeastern Iran, with communities also present in regions such as Golestan Province.
|
E1017621
|
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: Lari | Statement: [Golestan Province, hasEthnicGroup, Lari]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lari Context triple: [Golestan Province, hasEthnicGroup, Lari]
-
A.
Lari
Lari is a regional dialect of the Sindhi language spoken primarily in parts of Sindh, Pakistan.
-
B.
Lari
Lari is a town in Kenya’s Central Region, known for its agricultural activities and its location within Kiambu County.
-
C.
Lai
The Lai are an indigenous ethnic group of the broader Mizo community, primarily inhabiting parts of northeast India and neighboring Myanmar, with their own distinct language and cultural traditions.
-
D.
Lai
Lai is a variant spelling of the Chinese surname Li, commonly found in Chinese-speaking communities and their diasporas.
-
E.
Lia
Lia is a Japanese singer best known for performing iconic anime theme songs, including the opening of Angel Beats!.
- 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: Lari Triple: [Golestan Province, hasEthnicGroup, Lari]
Generated description
The Lari are an Iranian ethnic group traditionally inhabiting parts of southern and southeastern Iran, with communities also present in regions such as Golestan Province.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lari Target entity description: The Lari are an Iranian ethnic group traditionally inhabiting parts of southern and southeastern Iran, with communities also present in regions such as Golestan Province.
-
A.
Lari
Lari is a regional dialect of the Sindhi language spoken primarily in parts of Sindh, Pakistan.
-
B.
Lari
Lari is a town in Kenya’s Central Region, known for its agricultural activities and its location within Kiambu County.
-
C.
Lai
The Lai are an indigenous ethnic group of the broader Mizo community, primarily inhabiting parts of northeast India and neighboring Myanmar, with their own distinct language and cultural traditions.
-
D.
Lai
Lai is a variant spelling of the Chinese surname Li, commonly found in Chinese-speaking communities and their diasporas.
-
E.
Lia
Lia is a Japanese singer best known for performing iconic anime theme songs, including the opening of Angel Beats!.
- 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_69d8076e64308190904fb5c93517c901 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d9804d8e3081909584c93df099859a |
completed | April 10, 2026, 10:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6cbd5139c8190aaec6487f074f251 |
completed | May 3, 2026, 4:15 a.m. |
| NEDg | Description generation | batch_69f6ce6278e081908864fba1db23ada0 |
completed | May 3, 2026, 4:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6cf547b188190b24c51e06a3b4d3c |
completed | May 3, 2026, 4:30 a.m. |
Created at: April 9, 2026, 8:56 p.m.