Triple

T10999269
Position Surface form Disambiguated ID Type / Status
Subject Dextre E259963 entity
Predicate manufacturer P490 FINISHED
Object MDA E238204 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: MDA | Statement: [Dextre, manufacturer, MDA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MDA
Context triple: [Dextre, manufacturer, MDA]
  • A. MDA
    MDA (Monochrome Display Adapter) is IBM's original text-only video display standard for early IBM PCs, providing high-resolution monochrome output without graphics capabilities.
  • B. MDA
    MDA is the state agency responsible for promoting and regulating Maryland’s agricultural industry, including farming, food safety, and related environmental programs.
  • C. MDA chosen
    MDA is a Canadian space technology company known for developing advanced satellite systems, robotics, and Earth observation solutions.
  • D. MDA
    MDA is the United States Missile Defense Agency, a Department of Defense organization responsible for developing and deploying systems to defend the U.S. and its allies against ballistic missile threats.
  • E. MDA
    MDA is the ICAO airline designator assigned to Mandarin Airlines, a Taiwanese regional carrier.
  • 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d796d5457c819096630246fa5f7076 completed April 9, 2026, 12:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69e34530ada081909dc58ff0261e93e7 completed April 18, 2026, 8:47 a.m.
Created at: April 8, 2026, 9:25 p.m.