Triple

T22334839
Position Surface form Disambiguated ID Type / Status
Subject Nastik E552117 entity
Predicate hasCastMember P2308 FINISHED
Object Ulhas
Ulhas was an Indian film actor known for his character roles in Hindi cinema during the mid-20th century.
 E1531886 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: Ulhas | Statement: [Nastik, hasCastMember, Ulhas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ulhas
Context triple: [Nastik, hasCastMember, Ulhas]
  • A. Bhandardara
    Bhandardara is a scenic hill station and lakeside village in Maharashtra, India, known for its waterfalls, forts, and tranquil natural surroundings.
  • B. Takshaka
    Takshaka is a prominent serpent king (naga) in Hindu mythology, best known for killing King Parikshit and thereby becoming the central target of King Janamejaya’s great snake sacrifice.
  • C. Narasimha Wadi
    Narasimha Wadi is a prominent Hindu pilgrimage town in Maharashtra, India, renowned for its sacred Dattatreya temple on the banks of the Krishna River.
  • D. Dhuleti
    Dhuleti is the vibrant second day of the Hindu festival of Holi, celebrated with the playful throwing of colored powders and water.
  • E. Vohra
    Vohra is an Indian surname commonly associated with Punjabi and North Indian communities, including notable figures in politics, business, and public life.
  • 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: Ulhas
Triple: [Nastik, hasCastMember, Ulhas]
Generated description
Ulhas was an Indian film actor known for his character roles in Hindi cinema during the mid-20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ulhas
Target entity description: Ulhas was an Indian film actor known for his character roles in Hindi cinema during the mid-20th century.
  • A. Bhandardara
    Bhandardara is a scenic hill station and lakeside village in Maharashtra, India, known for its waterfalls, forts, and tranquil natural surroundings.
  • B. Takshaka
    Takshaka is a prominent serpent king (naga) in Hindu mythology, best known for killing King Parikshit and thereby becoming the central target of King Janamejaya’s great snake sacrifice.
  • C. Narasimha Wadi
    Narasimha Wadi is a prominent Hindu pilgrimage town in Maharashtra, India, renowned for its sacred Dattatreya temple on the banks of the Krishna River.
  • D. Dhuleti
    Dhuleti is the vibrant second day of the Hindu festival of Holi, celebrated with the playful throwing of colored powders and water.
  • E. Vohra
    Vohra is an Indian surname commonly associated with Punjabi and North Indian communities, including notable figures in politics, business, and public life.
  • 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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1577e35f48190b11789d80182653e completed April 29, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ae05458e88190941ac539297867fc completed May 18, 2026, 9:48 a.m.
NEDg Description generation batch_6a0ae1556010819099f891c6af11a2d5 completed May 18, 2026, 9:52 a.m.
NED2 Entity disambiguation (via description) batch_6a0ae1cb8d908190937609e2bd554036 completed May 18, 2026, 9:54 a.m.
Created at: April 16, 2026, 8:43 p.m.