Triple

T3665705
Position Surface form Disambiguated ID Type / Status
Subject CompEd E77753 entity
Predicate acronym P43 FINISHED
Object CompEd E77753 NE FINISHED

How this triple was built (2 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: CompEd | Statement: [CompEd, acronym, CompEd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CompEd
Context triple: [CompEd, acronym, CompEd]
  • A. CompEd chosen
    CompEd is an international ACM SIGCSE conference focused on research and innovation in computing education.
  • B. OpenLearning
    OpenLearning is an online education platform that hosts and delivers massive open online courses (MOOCs) from institutions and educators worldwide.
  • C. Education Center
    The Education Center is a learning facility within the United States Holocaust Memorial Museum that provides educational programs, resources, and interactive experiences to teach about the history and lessons of the Holocaust.
  • D. LinkedIn Learning
    LinkedIn Learning is an online educational platform offering video-based courses in business, technology, and creative skills, integrated with LinkedIn for professional development and career growth.
  • E. Edu
    Edu is a local government area in Kwara State, Nigeria, known for its predominantly Nupe-speaking communities and agrarian economy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad85dfc4dc8190a441864202ab2a7a completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc400352081908c16a6a7670eb52a completed March 8, 2026, 6:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4884bd50c8190a334e9aadc734364 completed March 13, 2026, 9:57 p.m.
Created at: March 8, 2026, 3:25 p.m.