Triple

T5128936
Position Surface form Disambiguated ID Type / Status
Subject Mrinal Sen E115647 entity
Predicate notableWork P4 FINISHED
Object Antareen
Antareen is a 1993 Indian Bengali-language film directed by Mrinal Sen, known for its introspective exploration of human isolation and relationships.
 E496019 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: Antareen | Statement: [Mrinal Sen, notableWork, Antareen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Antareen
Context triple: [Mrinal Sen, notableWork, Antareen]
  • A. Aternus
    Aternus is an ancient river in central Italy historically associated with the territory of the Marrucini people.
  • B. Mylasa
    Mylasa was an important ancient city of Caria in southwestern Anatolia, known as a political and religious center, particularly for the worship of Zeus.
  • C. Teia
    Teia was the final king of the Ostrogoths in Italy, known for leading their last resistance against the Eastern Roman Empire in the mid-6th century.
  • D. Aegitna
    Aegitna is the ancient name of the city now known as Cannes on the French Riviera.
  • E. Euthenia
    Euthenia is a minor Greek goddess associated with prosperity, abundance, and material plenty.
  • 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: Antareen
Triple: [Mrinal Sen, notableWork, Antareen]
Generated description
Antareen is a 1993 Indian Bengali-language film directed by Mrinal Sen, known for its introspective exploration of human isolation and relationships.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Antareen
Target entity description: Antareen is a 1993 Indian Bengali-language film directed by Mrinal Sen, known for its introspective exploration of human isolation and relationships.
  • A. Aternus
    Aternus is an ancient river in central Italy historically associated with the territory of the Marrucini people.
  • B. Mylasa
    Mylasa was an important ancient city of Caria in southwestern Anatolia, known as a political and religious center, particularly for the worship of Zeus.
  • C. Teia
    Teia was the final king of the Ostrogoths in Italy, known for leading their last resistance against the Eastern Roman Empire in the mid-6th century.
  • D. Aegitna
    Aegitna is the ancient name of the city now known as Cannes on the French Riviera.
  • E. Euthenia
    Euthenia is a minor Greek goddess associated with prosperity, abundance, and material plenty.
  • 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_69bd444426bc819099ccd23f141e22aa completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7825facc8190b2a6c17216290b5c completed March 20, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec4c23d5c8190883a297254d9c80d completed March 21, 2026, 4:18 p.m.
NEDg Description generation batch_69bec6620aac8190a820190e7facd70a completed March 21, 2026, 4:25 p.m.
NED2 Entity disambiguation (via description) batch_69bec70062f48190baae277e6f8c5c4e completed March 21, 2026, 4:27 p.m.
Created at: March 20, 2026, 1:42 p.m.