Triple

T5792144
Position Surface form Disambiguated ID Type / Status
Subject Doordarshan E128419 entity
Predicate notableProgram P4 FINISHED
Object Hum Log
Hum Log is an Indian television soap opera that aired in the 1980s and is widely regarded as the country’s first long-running TV serial.
E546428 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: Hum Log | Statement: [Doordarshan, notableProgram, Hum Log]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hum Log
Context triple: [Doordarshan, notableProgram, Hum Log]
  • A. Hubuna
    Hubuna is a town in southwestern Saudi Arabia located within the Najran Region near the Yemeni border.
  • B. Billu
    Billu is a 2009 Indian Hindi-language comedy-drama film about a poor village barber whose life changes when a Bollywood superstar, played by Shah Rukh Khan, visits his town.
  • C. Har Mar Superstar
    Har Mar Superstar is the stage name of Sean Tillmann, an American singer, songwriter, and performer known for his soulful pop/R&B music and humorous, often provocative live shows.
  • D. Hangmatana
    Hangmatana is the Old Persian name for Ecbatana, the ancient capital city of the Median Empire in what is now western Iran.
  • E. Hullabaloo
    Hullabaloo was a 1960s American musical variety television show that featured popular rock and pop performers of the era.
  • 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: Hum Log
Triple: [Doordarshan, notableProgram, Hum Log]
Generated description
Hum Log is an Indian television soap opera that aired in the 1980s and is widely regarded as the country’s first long-running TV serial.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hum Log
Target entity description: Hum Log is an Indian television soap opera that aired in the 1980s and is widely regarded as the country’s first long-running TV serial.
  • A. Hubuna
    Hubuna is a town in southwestern Saudi Arabia located within the Najran Region near the Yemeni border.
  • B. Billu
    Billu is a 2009 Indian Hindi-language comedy-drama film about a poor village barber whose life changes when a Bollywood superstar, played by Shah Rukh Khan, visits his town.
  • C. Har Mar Superstar
    Har Mar Superstar is the stage name of Sean Tillmann, an American singer, songwriter, and performer known for his soulful pop/R&B music and humorous, often provocative live shows.
  • D. Hangmatana
    Hangmatana is the Old Persian name for Ecbatana, the ancient capital city of the Median Empire in what is now western Iran.
  • E. Hullabaloo
    Hullabaloo was a 1960s American musical variety television show that featured popular rock and pop performers of the era.
  • 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_69c00845ca68819081a2ce3ecca577f7 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02a5870b88190bbfaac2782635128 completed March 22, 2026, 5:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c09824c7f0819095565e0f29b3a508 completed March 23, 2026, 1:32 a.m.
NEDg Description generation batch_69c098a0325c81909a1326b94e40ed50 completed March 23, 2026, 1:34 a.m.
NED2 Entity disambiguation (via description) batch_69c09943deec819085992c4e44050a34 completed March 23, 2026, 1:37 a.m.
Created at: March 22, 2026, 3:51 p.m.