Triple

T5772799
Position Surface form Disambiguated ID Type / Status
Subject Cuddalore E127366 entity
Predicate hasNeighbourhood P4813 FINISHED
Object Manjakuppam
Manjakuppam is a residential and commercial neighborhood in the coastal town of Cuddalore in the Indian state of Tamil Nadu.
 E544886 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: Manjakuppam | Statement: [Cuddalore, hasNeighbourhood, Manjakuppam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Manjakuppam
Context triple: [Cuddalore, hasNeighbourhood, Manjakuppam]
  • A. Dosa
    Dosa is a popular South Indian fermented crepe made from rice and lentil batter, commonly eaten as a savory breakfast or snack.
  • B. Kanchipuri
    Kanchipuri is another name for Kanchipuram, an ancient South Indian city renowned for its historic temples and silk saree weaving tradition.
  • C. Panketal
    Panketal is a municipality in the Barnim district of Brandenburg, Germany, located northeast of Berlin and known as a residential suburb within the Berlin metropolitan area.
  • D. Rozogi
    Rozogi is a village in northern Poland that serves as a local administrative and service center within the Warmian-Masurian Voivodeship.
  • E. Idli
    Idli is a soft, steamed South Indian rice-and-lentil cake commonly eaten for breakfast and often served with sambar and chutneys.
  • 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: Manjakuppam
Triple: [Cuddalore, hasNeighbourhood, Manjakuppam]
Generated description
Manjakuppam is a residential and commercial neighborhood in the coastal town of Cuddalore in the Indian state of Tamil Nadu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Manjakuppam
Target entity description: Manjakuppam is a residential and commercial neighborhood in the coastal town of Cuddalore in the Indian state of Tamil Nadu.
  • A. Dosa
    Dosa is a popular South Indian fermented crepe made from rice and lentil batter, commonly eaten as a savory breakfast or snack.
  • B. Kanchipuri
    Kanchipuri is another name for Kanchipuram, an ancient South Indian city renowned for its historic temples and silk saree weaving tradition.
  • C. Panketal
    Panketal is a municipality in the Barnim district of Brandenburg, Germany, located northeast of Berlin and known as a residential suburb within the Berlin metropolitan area.
  • D. Rozogi
    Rozogi is a village in northern Poland that serves as a local administrative and service center within the Warmian-Masurian Voivodeship.
  • E. Idli
    Idli is a soft, steamed South Indian rice-and-lentil cake commonly eaten for breakfast and often served with sambar and chutneys.
  • 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_69c00834f6308190851b0abeddd8ed7e completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c029adda188190a5c26c363614145f completed March 22, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e686ad88190b34e5e94145b44dc completed March 22, 2026, 11:42 p.m.
NEDg Description generation batch_69c08d238384819089104f5c778ec315 completed March 23, 2026, 12:45 a.m.
NED2 Entity disambiguation (via description) batch_69c08dac9eec8190996f6c537777801b completed March 23, 2026, 12:47 a.m.
Created at: March 22, 2026, 3:50 p.m.