Triple

T5969937
Position Surface form Disambiguated ID Type / Status
Subject College of Humanities (EPFL) E132846 entity
Predicate abbreviation P43 FINISHED
Object CDH
CDH is the College of Humanities at EPFL, responsible for teaching and research in human and social sciences within the Swiss engineering and technology university.
E558702 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: CDH | Statement: [College of Humanities (EPFL), abbreviation, CDH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CDH
Context triple: [College of Humanities (EPFL), abbreviation, CDH]
  • A. Cloudera
    Cloudera is an enterprise data management and analytics company best known for its platform built on Apache Hadoop and related open-source big data technologies.
  • B. HDP
    HDP is the acronym for Heritage Documentation Programs, a U.S. National Park Service initiative that records and preserves historic sites, structures, and engineering works through detailed documentation.
  • C. Hadoop
    Hadoop is an open-source framework that enables distributed storage and parallel processing of large data sets across clusters of commodity hardware.
  • D. Apache Hive
    Apache Hive is a data warehouse and SQL-like query system built on top of Hadoop for managing and analyzing large datasets stored in distributed storage.
  • E. Amazon EMR
    Amazon EMR is a managed big data platform on AWS that simplifies running large-scale data processing frameworks like Apache Hadoop and Spark on elastic cloud clusters.
  • 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: CDH
Triple: [College of Humanities (EPFL), abbreviation, CDH]
Generated description
CDH is the College of Humanities at EPFL, responsible for teaching and research in human and social sciences within the Swiss engineering and technology university.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CDH
Target entity description: CDH is the College of Humanities at EPFL, responsible for teaching and research in human and social sciences within the Swiss engineering and technology university.
  • A. Cloudera
    Cloudera is an enterprise data management and analytics company best known for its platform built on Apache Hadoop and related open-source big data technologies.
  • B. HDP
    HDP is the acronym for Heritage Documentation Programs, a U.S. National Park Service initiative that records and preserves historic sites, structures, and engineering works through detailed documentation.
  • C. Hadoop
    Hadoop is an open-source framework that enables distributed storage and parallel processing of large data sets across clusters of commodity hardware.
  • D. Apache Hive
    Apache Hive is a data warehouse and SQL-like query system built on top of Hadoop for managing and analyzing large datasets stored in distributed storage.
  • E. Amazon EMR
    Amazon EMR is a managed big data platform on AWS that simplifies running large-scale data processing frameworks like Apache Hadoop and Spark on elastic cloud clusters.
  • 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_69c0086deab081908550159ca23eec9b completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03a4263e8819084e98e6c016c9532 completed March 22, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e40506848190843971e772d56054 completed March 23, 2026, 6:56 a.m.
NEDg Description generation batch_69c0edb0a0808190b2b6f5fc0d7b7913 completed March 23, 2026, 7:37 a.m.
NED2 Entity disambiguation (via description) batch_69c0ee2ffbc88190a256b5cb8a98f382 completed March 23, 2026, 7:39 a.m.
Created at: March 22, 2026, 4:03 p.m.