Triple

T18763837
Position Surface form Disambiguated ID Type / Status
Subject Turbomeca E458842 entity
Predicate notableEngineFamily P18926 FINISHED
Object RTM322 NE NERFINISHED

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: RTM322 | Statement: [Turbomeca, notableEngineFamily, RTM322]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RTM322
Context triple: [Turbomeca, notableEngineFamily, RTM322]
  • A. RTM322 chosen
    RTM322 is a turboshaft aircraft engine developed jointly by Rolls-Royce and Turbomeca, widely used to power military and transport helicopters such as the NH90 and Apache.
  • B. RTM322-01/9
    RTM322-01/9 is a specific variant of the Rolls-Royce Turbomeca RTM322 turboshaft engine, optimized for use in modern military and naval helicopters.
  • C. RM-422
    RM-422 is a regional road in the municipality of Abanilla, Spain, providing local transport connectivity within the area.
  • D. LM32
    LM32 is a 32-bit soft microprocessor core architecture developed by Lattice Semiconductor, commonly used in FPGA-based embedded systems.
  • E. RTM
    RTM is the commonly used abbreviation for Rosetta Terminology Mapping, a system for standardizing and aligning terminology across different datasets or domains.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d395dba0819087568404508590cb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e58d82297c81909f720e2637cec737 completed April 20, 2026, 2:20 a.m.
Created at: April 10, 2026, 11:52 a.m.