Triple

T5602218
Position Surface form Disambiguated ID Type / Status
Subject Manipal Institute of Technology E147145 entity
Predicate offersDegree P49 FINISHED
Object MCA
MCA is a postgraduate professional degree in computer applications that focuses on advanced software development, programming, and IT skills.
E533758 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: MCA | Statement: [Manipal Institute of Technology, offersDegree, MCA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MCA
Context triple: [Manipal Institute of Technology, offersDegree, MCA]
  • A. MCA
    MCA was a major American record label and entertainment company known for signing prominent artists and producing a wide range of popular music releases.
  • B. MCA
    MCA is the UK government executive agency responsible for maritime safety, search and rescue coordination, and preventing pollution from ships in UK waters.
  • C. MCA
    MCA is a prominent Algerian football club based in Algiers, officially known as Mouloudia Club d'Alger.
  • D. MCC
    MCC is the abbreviated name of Belgium’s naval branch within the Belgian Armed Forces.
  • E. MCC
    MCC is one of the shorter companion races of the Ultra-Trail du Mont-Blanc trail-running event, typically designed for newer trail runners and local participants.
  • 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: MCA
Triple: [Manipal Institute of Technology, offersDegree, MCA]
Generated description
MCA is a postgraduate professional degree in computer applications that focuses on advanced software development, programming, and IT skills.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MCA
Target entity description: MCA is a postgraduate professional degree in computer applications that focuses on advanced software development, programming, and IT skills.
  • A. MCA
    MCA was a major American record label and entertainment company known for signing prominent artists and producing a wide range of popular music releases.
  • B. MCA
    MCA is the UK government executive agency responsible for maritime safety, search and rescue coordination, and preventing pollution from ships in UK waters.
  • C. MCA
    MCA is a prominent Algerian football club based in Algiers, officially known as Mouloudia Club d'Alger.
  • D. MCC
    MCC is the abbreviated name of Belgium’s naval branch within the Belgian Armed Forces.
  • E. MCC
    MCC is one of the shorter companion races of the Ultra-Trail du Mont-Blanc trail-running event, typically designed for newer trail runners and local participants.
  • 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_69c009043d648190a7af89698ccf1e3e completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c020dbd6dc8190ba011876c205754e completed March 22, 2026, 5:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c02873b1dc8190b11a6c069f3e4f7e completed March 22, 2026, 5:35 p.m.
NEDg Description generation batch_69c035f54f6c8190badbfd800012c399 completed March 22, 2026, 6:33 p.m.
NED2 Entity disambiguation (via description) batch_69c036f0edb48190bfa74f7f2c9d9ab1 completed March 22, 2026, 6:37 p.m.
Created at: March 22, 2026, 3:39 p.m.