Triple

T7999604
Position Surface form Disambiguated ID Type / Status
Subject Microsoft Access E186212 entity
Predicate supports P516 FINISHED
Object ADO E182224 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: ADO | Statement: [Microsoft Access, supports, ADO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ADO
Context triple: [Microsoft Access, supports, ADO]
  • A. ODB
    ODB was the stage name of Ol' Dirty Bastard, a founding member of the Wu-Tang Clan known for his wild persona, distinctive vocal style, and influential role in 1990s hip-hop.
  • B. ADB
    ADB is a regional multilateral development bank that promotes economic growth and cooperation in Asia and the Pacific through loans, grants, and technical assistance.
  • C. ADB
    ADB (Apple Desktop Bus) is a now-obsolete serial interface developed by Apple for connecting low-speed input devices like keyboards and mice to Macintosh computers.
  • D. ADB
    ADB is the IATA airport code for Adnan Menderes Airport, the main international airport serving İzmir, Turkey.
  • E. ADO.NET chosen
    ADO.NET is a data access framework in the .NET ecosystem that enables applications to connect to, retrieve, manipulate, and update data from various data sources such as relational databases and XML.
  • 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_69ca82aaaf24819084b94d18f699ba53 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c9b67988190a8a4a2c960017400 completed March 31, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe114372c819086f06e184d5ebde2 completed March 31, 2026, 2:58 p.m.
Created at: March 30, 2026, 5:17 p.m.