Triple

T2561515
Position Surface form Disambiguated ID Type / Status
Subject OLE DB E57250 entity
Predicate basedOn P98 FINISHED
Object COM E183319 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: COM | Statement: [OLE DB, basedOn, COM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: COM
Context triple: [OLE DB, basedOn, COM]
  • A. COM chosen
    COM (Component Object Model) is a Microsoft-developed software architecture that enables interprocess communication and reusable binary components across different programming languages and applications on Windows.
  • B. CM
    CM is the post-nominal letters used to denote a Member of the Order of Canada, one of the country’s highest civilian honors.
  • C. CM
    CM is the standard abbreviation for "Concrete Mathematics," a well-known textbook by Graham, Knuth, and Patashnik that blends discrete mathematics with concrete problem-solving techniques.
  • D. CM
    CM is the two-letter ISO 3166-1 alpha-2 country code assigned to Cameroon.
  • E. CM
    CM is the commonly used abbreviation for the Committee of Ministers, the decision-making body of the Council of Europe composed of the foreign ministers of member states or their representatives.
  • 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_69ab4a4ef9008190a0e6d4422b9418b7 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd336183c819084ed7de8ccc4c548 completed March 7, 2026, 7:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69af5d233dbc81909feb1127cffb027f completed March 9, 2026, 11:52 p.m.
Created at: March 6, 2026, 9:48 p.m.