Triple

T8916831
Position Surface form Disambiguated ID Type / Status
Subject Sumerian King List E212313 entity
Predicate listsCity P51257 FINISHED
Object Awan
Awan was an ancient city-state of the Elamite civilization, known from Mesopotamian sources as an early political center in southwestern Iran.
 E766876 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: Awan | Statement: [Sumerian King List, listsCity, Awan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Awan
Context triple: [Sumerian King List, listsCity, Awan]
  • A. Mangal
    Mangal is a given name most notably borne by Mangal Pandey, an Indian soldier whose actions helped spark the Indian Rebellion of 1857.
  • B. Mangal
    Mangal is a Pashtun tribe traditionally associated with the Karlani tribal confederation in Afghanistan and Pakistan.
  • C. Miraj
    Miraj is a prominent city in Maharashtra, India, known as a regional commercial and medical hub and for its historical and cultural significance.
  • D. Makani
    Makani was an experimental Alphabet X (formerly Google X) project that developed airborne wind turbines using tethered kites to generate renewable energy.
  • E. Maglan
    Maglan is an elite Israeli special forces unit known for conducting deep reconnaissance and precision strike missions behind enemy lines.
  • 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: Awan
Triple: [Sumerian King List, listsCity, Awan]
Generated description
Awan was an ancient city-state of the Elamite civilization, known from Mesopotamian sources as an early political center in southwestern Iran.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Awan
Target entity description: Awan was an ancient city-state of the Elamite civilization, known from Mesopotamian sources as an early political center in southwestern Iran.
  • A. Mangal
    Mangal is a given name most notably borne by Mangal Pandey, an Indian soldier whose actions helped spark the Indian Rebellion of 1857.
  • B. Mangal
    Mangal is a Pashtun tribe traditionally associated with the Karlani tribal confederation in Afghanistan and Pakistan.
  • C. Miraj
    Miraj is a prominent city in Maharashtra, India, known as a regional commercial and medical hub and for its historical and cultural significance.
  • D. Makani
    Makani was an experimental Alphabet X (formerly Google X) project that developed airborne wind turbines using tethered kites to generate renewable energy.
  • E. Maglan
    Maglan is an elite Israeli special forces unit known for conducting deep reconnaissance and precision strike missions behind enemy lines.
  • 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_69ca8393b1808190bd4336787ffa2c40 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6610cd48819090a184c5f9465626 completed April 1, 2026, 12:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba4567a88190855b964bc6e3ac6f completed April 3, 2026, 1:01 p.m.
NEDg Description generation batch_69cfbb0db6848190a375196a021d1bb9 completed April 3, 2026, 1:05 p.m.
NED2 Entity disambiguation (via description) batch_69cfbf7f551c819089830d16fe55599e completed April 3, 2026, 1:24 p.m.
Created at: March 30, 2026, 6:56 p.m.