Triple

T7571921
Position Surface form Disambiguated ID Type / Status
Subject Usha Kundu, MD College of Health E179262 entity
Predicate abbreviation P43 FINISHED
Object UKCOH
UKCOH is the Usha Kundu, MD College of Health, an academic institution focused on health and medical education.
 E673718 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: UKCOH | Statement: [Usha Kundu, MD College of Health, abbreviation, UKCOH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UKCOH
Context triple: [Usha Kundu, MD College of Health, abbreviation, UKCOH]
  • A. EUCO
    EUCO is the commonly used abbreviation for the European Council, the institution that defines the European Union’s overall political direction and priorities.
  • B. LPCO
    LPCO is the ICAO airport code assigned to Coimbra Airport in Portugal.
  • C. OUCC
    OUCC is the abbreviation for Oxford University Cricket Club, the historic cricket team representing the University of Oxford.
  • D. UKSC
    UKSC is the abbreviation for UK Space Command, the United Kingdom’s military organization responsible for space operations and defense.
  • E. UKSC
    UKSC is the commonly used abbreviation for the Supreme Court of the United Kingdom, the highest appellate court in the UK for civil cases and most criminal cases.
  • 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: UKCOH
Triple: [Usha Kundu, MD College of Health, abbreviation, UKCOH]
Generated description
UKCOH is the Usha Kundu, MD College of Health, an academic institution focused on health and medical education.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UKCOH
Target entity description: UKCOH is the Usha Kundu, MD College of Health, an academic institution focused on health and medical education.
  • A. EUCO
    EUCO is the commonly used abbreviation for the European Council, the institution that defines the European Union’s overall political direction and priorities.
  • B. LPCO
    LPCO is the ICAO airport code assigned to Coimbra Airport in Portugal.
  • C. OUCC
    OUCC is the abbreviation for Oxford University Cricket Club, the historic cricket team representing the University of Oxford.
  • D. UKSC
    UKSC is the abbreviation for UK Space Command, the United Kingdom’s military organization responsible for space operations and defense.
  • E. UKSC
    UKSC is the commonly used abbreviation for the Supreme Court of the United Kingdom, the highest appellate court in the UK for civil cases and most criminal cases.
  • 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_69c69f316e50819081a271c85c06f918 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c6f921b458819092e565a4d099bbaf completed March 27, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69c856e7c5b48190b6f53f8d14ea753d completed March 28, 2026, 10:32 p.m.
NEDg Description generation batch_69c858aea4fc81908be95d0d4e3f1072 completed March 28, 2026, 10:39 p.m.
NED2 Entity disambiguation (via description) batch_69c85919f85081908558f8e8d4b9d057 completed March 28, 2026, 10:41 p.m.
Created at: March 27, 2026, 3:51 p.m.