Triple

T23415686
Position Surface form Disambiguated ID Type / Status
Subject Hasanuddin University E560198 entity
Predicate hasAcronym P43 FINISHED
Object UNHAS
UNHAS is the commonly used acronym for Hasanuddin University, a major public university located in Makassar, Indonesia.
 E1587164 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: UNHAS | Statement: [Hasanuddin University, hasAcronym, UNHAS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UNHAS
Context triple: [Hasanuddin University, hasAcronym, UNHAS]
  • A. UNA
    UNA is the stock ticker symbol for Unilever, a major multinational consumer goods company known for its wide range of food, personal care, and household products.
  • B. UNA
    UNA is the commonly used acronym for the National University of Asunción, a major public higher education institution in Paraguay.
  • C. UNA
    UNA is a public university located in Florence, Alabama, known for its regional academic programs and historic campus.
  • D. UNA
    UNA is the commonly used acronym for the National University of Costa Rica, a major public higher education and research institution in the country.
  • E. UNAH
    UNAH is the main public higher education institution in Honduras, known for its comprehensive academic programs and central role in the country’s research and professional training.
  • 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: UNHAS
Triple: [Hasanuddin University, hasAcronym, UNHAS]
Generated description
UNHAS is the commonly used acronym for Hasanuddin University, a major public university located in Makassar, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UNHAS
Target entity description: UNHAS is the commonly used acronym for Hasanuddin University, a major public university located in Makassar, Indonesia.
  • A. UNA
    UNA is the stock ticker symbol for Unilever, a major multinational consumer goods company known for its wide range of food, personal care, and household products.
  • B. UNA
    UNA is the commonly used acronym for the National University of Asunción, a major public higher education institution in Paraguay.
  • C. UNA
    UNA is a public university located in Florence, Alabama, known for its regional academic programs and historic campus.
  • D. UNA
    UNA is the commonly used acronym for the National University of Costa Rica, a major public higher education and research institution in the country.
  • E. UNAH
    UNAH is the main public higher education institution in Honduras, known for its comprehensive academic programs and central role in the country’s research and professional training.
  • 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_69e2454b3a5881909c64773dc8a5d289 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a515fe048190adefdefaeff76cfd completed April 29, 2026, 6:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c679d40c48190b921ac170c6c36cf completed May 19, 2026, 1:37 p.m.
NEDg Description generation batch_6a0c72156130819082e1d07262e144ca completed May 19, 2026, 2:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0c770386a8819098358513016ae5ab completed May 19, 2026, 2:43 p.m.
Created at: April 17, 2026, 5:39 p.m.