Triple

T8558528
Position Surface form Disambiguated ID Type / Status
Subject AVM Productions E202634 entity
Predicate hasNotableWork P4 FINISHED
Object Sahodhari
Sahodhari is an Indian Tamil-language film produced by the prominent Chennai-based studio AVM Productions.
 E743848 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: Sahodhari | Statement: [AVM Productions, hasNotableWork, Sahodhari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sahodhari
Context triple: [AVM Productions, hasNotableWork, Sahodhari]
  • A. Sarabha
    Sarabha is an Indian surname most notably associated with Kartar Singh Sarabha, a prominent revolutionary in the Indian independence movement.
  • B. Savindan
    Savindan is the Serbian Orthodox holiday and cultural celebration honoring Saint Sava, the first Archbishop of the Serbian Church and patron of education.
  • C. Salbai
    Salbai is a historical location in India known primarily as the site where the 1782 Treaty of Salbai was concluded between the British East India Company and the Maratha Empire.
  • D. Sohi
    Sohi is a Punjabi-origin surname commonly found among people from the Indian subcontinent and their diaspora.
  • E. Sureth
    Sureth is a modern Eastern Aramaic language spoken primarily by Assyrian communities in parts of Iraq, Syria, Iran, and the diaspora.
  • 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: Sahodhari
Triple: [AVM Productions, hasNotableWork, Sahodhari]
Generated description
Sahodhari is an Indian Tamil-language film produced by the prominent Chennai-based studio AVM Productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sahodhari
Target entity description: Sahodhari is an Indian Tamil-language film produced by the prominent Chennai-based studio AVM Productions.
  • A. Sarabha
    Sarabha is an Indian surname most notably associated with Kartar Singh Sarabha, a prominent revolutionary in the Indian independence movement.
  • B. Savindan
    Savindan is the Serbian Orthodox holiday and cultural celebration honoring Saint Sava, the first Archbishop of the Serbian Church and patron of education.
  • C. Salbai
    Salbai is a historical location in India known primarily as the site where the 1782 Treaty of Salbai was concluded between the British East India Company and the Maratha Empire.
  • D. Sohi
    Sohi is a Punjabi-origin surname commonly found among people from the Indian subcontinent and their diaspora.
  • E. Sureth
    Sureth is a modern Eastern Aramaic language spoken primarily by Assyrian communities in parts of Iraq, Syria, Iran, and the diaspora.
  • 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_69ca8326e6c881908ff720d6abaebdc5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe9485dd88190bc2cf2adf39d48ee completed March 31, 2026, 3:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce89455dcc819088bdf5a2f653da17 completed April 2, 2026, 3:20 p.m.
NEDg Description generation batch_69ce8a9ce1a08190a579f7f7a0319d01 completed April 2, 2026, 3:26 p.m.
NED2 Entity disambiguation (via description) batch_69ce8bdf1f148190ac832424661bd8e5 completed April 2, 2026, 3:31 p.m.
Created at: March 30, 2026, 6:20 p.m.