Triple

T8667469
Position Surface form Disambiguated ID Type / Status
Subject Ajith Kumar E205711 entity
Predicate notableWork P4 FINISHED
Object Thunivu
Thunivu is a 2023 Tamil-language action heist film starring Ajith Kumar, known for its high-octane sequences and socially charged storyline.
E749972 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: Thunivu | Statement: [Ajith Kumar, notableWork, Thunivu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thunivu
Context triple: [Ajith Kumar, notableWork, Thunivu]
  • A. Świecie
    Świecie is a historic town in northern Poland, located in the Kuyavian-Pomeranian Voivodeship and known for its medieval castle and position near the confluence of the Vistula and Wda rivers.
  • B. Keamari
    Keamari is a coastal neighborhood and historic harbor area of Karachi, Pakistan, known for its docks, ferry services, and role as a gateway to the city’s port and nearby islands.
  • C. Umma
    Umma was an important Sumerian city-state in ancient Mesopotamia, known for its frequent territorial conflicts with the neighboring city-state of Lagash.
  • D. Eua
    Eua is the Greek form of the name Eve, the first woman in the Biblical creation narrative.
  • E. Verden
    Verden is a historic town in Lower Saxony, Germany, known for its medieval cathedral and location along the Weser River.
  • 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: Thunivu
Triple: [Ajith Kumar, notableWork, Thunivu]
Generated description
Thunivu is a 2023 Tamil-language action heist film starring Ajith Kumar, known for its high-octane sequences and socially charged storyline.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thunivu
Target entity description: Thunivu is a 2023 Tamil-language action heist film starring Ajith Kumar, known for its high-octane sequences and socially charged storyline.
  • A. Świecie
    Świecie is a historic town in northern Poland, located in the Kuyavian-Pomeranian Voivodeship and known for its medieval castle and position near the confluence of the Vistula and Wda rivers.
  • B. Keamari
    Keamari is a coastal neighborhood and historic harbor area of Karachi, Pakistan, known for its docks, ferry services, and role as a gateway to the city’s port and nearby islands.
  • C. Umma
    Umma was an important Sumerian city-state in ancient Mesopotamia, known for its frequent territorial conflicts with the neighboring city-state of Lagash.
  • D. Eua
    Eua is the Greek form of the name Eve, the first woman in the Biblical creation narrative.
  • E. Verden
    Verden is a historic town in Lower Saxony, Germany, known for its medieval cathedral and location along the Weser River.
  • 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_69ca83516ae88190aefe034b3bc589e3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc48a34b808190aa9aed9cdb2900e6 completed March 31, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69cecd1ca88c8190a3b2ca79a7204248 completed April 2, 2026, 8:10 p.m.
NEDg Description generation batch_69cece8fcbcc8190832a66287bc8f833 completed April 2, 2026, 8:16 p.m.
NED2 Entity disambiguation (via description) batch_69cecff48600819086a15700cb947056 completed April 2, 2026, 8:22 p.m.
Created at: March 30, 2026, 6:31 p.m.