Triple

T15758813
Position Surface form Disambiguated ID Type / Status
Subject Amorite dynasty of Mari E382038 entity
Predicate sourceOfKnowledge P4092 FINISHED
Object Mari archives
The Mari archives are a vast collection of cuneiform tablets from the ancient city of Mari that provide crucial insights into the political, economic, and social life of the Amorite period in Mesopotamia.
E1175154 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: Mari archives | Statement: [Amorite dynasty of Mari, sourceOfKnowledge, Mari archives]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mari archives
Context triple: [Amorite dynasty of Mari, sourceOfKnowledge, Mari archives]
  • A. MAR
    MAR is the three-letter ISO 3166-1 alpha-3 country code assigned to Morocco.
  • B. MAR
    MAR is the stock ticker symbol for Marriott International, a leading global hotel and lodging company.
  • C. Marg
    Marg is a given name, typically a shortened form of Margaret, used primarily in English-speaking contexts.
  • D. Mari
    Mari is a character in Paulo Coelho's novel "Veronika Decides to Die," portrayed as a fellow patient in the mental institution who struggles with anxiety and societal expectations.
  • E. Mari
    Mari is the central character of the film "Return to Sender," around whom the story’s psychological drama and suspense unfold.
  • 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: Mari archives
Triple: [Amorite dynasty of Mari, sourceOfKnowledge, Mari archives]
Generated description
The Mari archives are a vast collection of cuneiform tablets from the ancient city of Mari that provide crucial insights into the political, economic, and social life of the Amorite period in Mesopotamia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mari archives
Target entity description: The Mari archives are a vast collection of cuneiform tablets from the ancient city of Mari that provide crucial insights into the political, economic, and social life of the Amorite period in Mesopotamia.
  • A. MAR
    MAR is the three-letter ISO 3166-1 alpha-3 country code assigned to Morocco.
  • B. MAR
    MAR is the stock ticker symbol for Marriott International, a leading global hotel and lodging company.
  • C. Marg
    Marg is a given name, typically a shortened form of Margaret, used primarily in English-speaking contexts.
  • D. Mari
    Mari is a character in Paulo Coelho's novel "Veronika Decides to Die," portrayed as a fellow patient in the mental institution who struggles with anxiety and societal expectations.
  • E. Mari
    Mari is the central character of the film "Return to Sender," around whom the story’s psychological drama and suspense unfold.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e050b35ea48190a758ee76a57b5451 completed April 16, 2026, 3 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8774eda08190a6231b4fd5027e6f completed May 9, 2026, 7:13 p.m.
NEDg Description generation batch_69ff885d33708190adb157afa7dc2e07 completed May 9, 2026, 7:17 p.m.
NED2 Entity disambiguation (via description) batch_69ff8948cc68819085c3953226236394 completed May 9, 2026, 7:21 p.m.
Created at: April 10, 2026, 4:47 a.m.