Triple

T27996795
Position Surface form Disambiguated ID Type / Status
Subject Kestrel engine E707033 entity
Predicate thrustVectorControlMethod P19997 FINISHED
Object gimbaled engine LITERAL 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: gimbaled engine | Statement: [Kestrel engine, thrustVectorControlMethod, gimbaled engine]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: thrustVectorControlMethod
Context triple: [Kestrel engine, thrustVectorControlMethod, gimbaled engine]
  • A. thrustVectorControl chosen
    Indicates the capability to direct or adjust the direction of thrust from a propulsion system to control an object's attitude or trajectory.
  • B. thrustControl
    Indicates a relationship where one entity regulates or adjusts the thrust output or propulsion force of another entity.
  • C. thrustVector
    Indicates the direction and magnitude of a force applied to propel or steer an object.
  • D. attitudeControlMethod
    Indicates the technique or mechanism used to control or adjust the orientation or pointing direction of an object (such as a vehicle or device).
  • E. thrustAugmentationMethod
    Indicates the method or technique used to increase or enhance thrust in a propulsion system.
  • F. None of above.

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_69ef96b980d88190a753b2f9a978595a completed April 27, 2026, 5:02 p.m.
NER Named-entity recognition batch_69f63bab984881909efaa8099e38fdf1 completed May 2, 2026, 6 p.m.
PD Predicate disambiguation batch_69f63710d17c819084cfe96e6df334fd completed May 2, 2026, 5:40 p.m.
Created at: April 27, 2026, 7:54 p.m.