Triple

T15004484
Position Surface form Disambiguated ID Type / Status
Subject administration of Akbar E377673 entity
Predicate office P3103 FINISHED
Object Mir Saman
Mir Saman was a high-ranking Mughal official who served as a key administrator under Emperor Akbar.
E1132054 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: Mir Saman | Statement: [administration of Akbar, office, Mir Saman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mir Saman
Context triple: [administration of Akbar, office, Mir Saman]
  • A. Samu
    Samu is a given name, commonly used as a short form or variant of Samuel in various cultures.
  • B. Laksamana
    Laksamana is a prominent heroic figure in Malay literary tradition, often depicted as a loyal and valiant warrior and royal commander.
  • C. Esse Baharmast
    Esse Baharmast is a former American soccer referee known for officiating at the highest levels of the sport, including Major League Soccer and the FIFA World Cup.
  • D. Sama
    Sama is an Austronesian language spoken by the Sama-Bajau people of the southern Philippines and parts of Malaysia and Indonesia.
  • E. Sama
    Sama is a town in northern Spain’s Asturias region, situated in the Nalón River valley and known historically for its coal-mining and industrial heritage.
  • 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: Mir Saman
Triple: [administration of Akbar, office, Mir Saman]
Generated description
Mir Saman was a high-ranking Mughal official who served as a key administrator under Emperor Akbar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mir Saman
Target entity description: Mir Saman was a high-ranking Mughal official who served as a key administrator under Emperor Akbar.
  • A. Samu
    Samu is a given name, commonly used as a short form or variant of Samuel in various cultures.
  • B. Laksamana
    Laksamana is a prominent heroic figure in Malay literary tradition, often depicted as a loyal and valiant warrior and royal commander.
  • C. Esse Baharmast
    Esse Baharmast is a former American soccer referee known for officiating at the highest levels of the sport, including Major League Soccer and the FIFA World Cup.
  • D. Sama
    Sama is a town in northern Spain’s Asturias region, situated in the Nalón River valley and known historically for its coal-mining and industrial heritage.
  • E. Sama
    Sama is an Austronesian language spoken by the Sama-Bajau people of the southern Philippines and parts of Malaysia and Indonesia.
  • 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_69d85cd3a3c881908c71fc424d459c17 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7322b5c81909089cbbf816e1436 completed April 15, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe96a04eec8190b347bf3637aba0bc completed May 9, 2026, 2:06 a.m.
NEDg Description generation batch_69fe98e182708190a013511c32d33315 completed May 9, 2026, 2:16 a.m.
NED2 Entity disambiguation (via description) batch_69fe9a48e85081909d70d8f44e3a54d7 completed May 9, 2026, 2:22 a.m.
Created at: April 10, 2026, 2:54 a.m.