Triple

T3338243
Position Surface form Disambiguated ID Type / Status
Subject College of Charleston E70191 entity
Predicate president P8 FINISHED
Object Andrew T. Hsu
Andrew T. Hsu is an academic leader and engineer who serves as the president of the College of Charleston.
E348999 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: Andrew T. Hsu | Statement: [College of Charleston, president, Andrew T. Hsu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew T. Hsu
Context triple: [College of Charleston, president, Andrew T. Hsu]
  • A. Kenneth Hsu
    Kenneth Hsu is a Swiss geologist and oceanographer known for his influential work on marine geology and the Messinian salinity crisis.
  • B. Eric S. Yuan
    Eric S. Yuan is a Chinese-American entrepreneur best known as the founder and CEO of Zoom Video Communications, a leading video conferencing platform.
  • C. Mung Chiang
    Mung Chiang is an engineer and academic leader known for his work in electrical and computer engineering and for serving as president of Purdue University.
  • D. Yu-Chi Ho
    Yu-Chi Ho is a prominent control theorist and engineer known for his pioneering contributions to optimal control, dynamic systems, and game theory.
  • E. Eugene Wong
    Eugene Wong is a computer scientist best known for his pioneering contributions to relational database theory and the development of early relational database systems.
  • 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: Andrew T. Hsu
Triple: [College of Charleston, president, Andrew T. Hsu]
Generated description
Andrew T. Hsu is an academic leader and engineer who serves as the president of the College of Charleston.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Andrew T. Hsu
Target entity description: Andrew T. Hsu is an academic leader and engineer who serves as the president of the College of Charleston.
  • A. Kenneth Hsu
    Kenneth Hsu is a Swiss geologist and oceanographer known for his influential work on marine geology and the Messinian salinity crisis.
  • B. Eric S. Yuan
    Eric S. Yuan is a Chinese-American entrepreneur best known as the founder and CEO of Zoom Video Communications, a leading video conferencing platform.
  • C. Mung Chiang
    Mung Chiang is an engineer and academic leader known for his work in electrical and computer engineering and for serving as president of Purdue University.
  • D. Yu-Chi Ho
    Yu-Chi Ho is a prominent control theorist and engineer known for his pioneering contributions to optimal control, dynamic systems, and game theory.
  • E. Eugene Wong
    Eugene Wong is a computer scientist best known for his pioneering contributions to relational database theory and the development of early relational database systems.
  • 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_69ad85a405e48190b6e68de7cf9f319e completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb1bd6c7c8190b7229de1433d8d20 completed March 8, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69b31a8ccc408190bae65d2d1a4d77bd completed March 12, 2026, 7:57 p.m.
NEDg Description generation batch_69b31aded5808190afbe4ae3ddb70428 completed March 12, 2026, 7:58 p.m.
NED2 Entity disambiguation (via description) batch_69b31c4665c081908d96878fc257fb76 completed March 12, 2026, 8:04 p.m.
Created at: March 8, 2026, 3:12 p.m.